Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2565 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 11.5143. Min Range: -11.5143
Max Act: 11.5143. Min Act: -0.1700
Data Index: 1423097 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5143. Min Range: -11.5143
Max Act: 11.3893. Min Act: -0.1700
Data Index: 5324432 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5143. Min Range: -11.5143
Max Act: 11.2018. Min Act: -0.1700
Data Index: 2866726 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5143. Min Range: -11.5143
Max Act: 11.2018. Min Act: -0.1700
Data Index: 3172075 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5143. Min Range: -11.5143
Max Act: 11.0768. Min Act: -0.1700
Data Index: 567302 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5143. Min Range: -11.5143
Max Act: 11.0768. Min Act: -0.1700
Data Index: 4076174 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5143. Min Range: -11.5143
Max Act: 10.9518. Min Act: -0.1700
Data Index: 3639071 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5143. Min Range: -11.5143
Max Act: 10.8893. Min Act: -0.1700
Data Index: 7528382 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5143. Min Range: -11.5143
Max Act: 10.8893. Min Act: -0.1700
Data Index: 2627666 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5143. Min Range: -11.5143
Max Act: 10.8893. Min Act: -0.1700
Data Index: 4423696 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5143. Min Range: -11.5143
Max Act: 10.7643. Min Act: -0.1700
Data Index: 384678 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5143. Min Range: -11.5143
Max Act: 10.8268. Min Act: -0.1700
Data Index: 3341782 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5143. Min Range: -11.5143
Max Act: 10.8268. Min Act: -0.1700
Data Index: 3733476 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5143. Min Range: -11.5143
Max Act: 10.8893. Min Act: -0.1700
Data Index: 8487679 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5143. Min Range: -11.5143
Max Act: 10.7643. Min Act: -0.1700
Data Index: 503163 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5143. Min Range: -11.5143
Max Act: 10.7643. Min Act: -0.1700
Data Index: 8646534 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5143. Min Range: -11.5143
Max Act: 10.7018. Min Act: -0.1700
Data Index: 8620188 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5143. Min Range: -11.5143
Max Act: 10.7643. Min Act: -0.1700
Data Index: 2866731 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5143. Min Range: -11.5143
Max Act: 10.7643. Min Act: -0.1700
Data Index: 5593286 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5143. Min Range: -11.5143
Max Act: 10.6393. Min Act: -0.1700
Data Index: 853954 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19