Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0349. Min Range: -7.0349
Max Act: 7.0349. Min Act: -0.1700
Data Index: 6351012 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0349. Min Range: -7.0349
Max Act: 6.8786. Min Act: -0.1700
Data Index: 2059558 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0349. Min Range: -7.0349
Max Act: 6.6286. Min Act: -0.1700
Data Index: 6276473 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0349. Min Range: -7.0349
Max Act: 6.6911. Min Act: -0.1700
Data Index: 689195 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0349. Min Range: -7.0349
Max Act: 6.6599. Min Act: -0.1700
Data Index: 7490278 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0349. Min Range: -7.0349
Max Act: 6.5974. Min Act: -0.1700
Data Index: 5103870 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0349. Min Range: -7.0349
Max Act: 6.5974. Min Act: -0.1700
Data Index: 7810568 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0349. Min Range: -7.0349
Max Act: 6.5661. Min Act: -0.1700
Data Index: 3363544 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0349. Min Range: -7.0349
Max Act: 6.5661. Min Act: -0.1700
Data Index: 6946880 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0349. Min Range: -7.0349
Max Act: 6.5349. Min Act: -0.1700
Data Index: 346477 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0349. Min Range: -7.0349
Max Act: 6.5349. Min Act: -0.1700
Data Index: 1810065 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0349. Min Range: -7.0349
Max Act: 6.5036. Min Act: -0.1700
Data Index: 5124020 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0349. Min Range: -7.0349
Max Act: 6.4411. Min Act: -0.1700
Data Index: 3460269 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0349. Min Range: -7.0349
Max Act: 6.4099. Min Act: -0.1700
Data Index: 581390 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0349. Min Range: -7.0349
Max Act: 6.3786. Min Act: -0.1700
Data Index: 6519430 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0349. Min Range: -7.0349
Max Act: 6.3786. Min Act: -0.1700
Data Index: 5479123 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0349. Min Range: -7.0349
Max Act: 6.3786. Min Act: -0.1700
Data Index: 1890011 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0349. Min Range: -7.0349
Max Act: 6.3786. Min Act: -0.1700
Data Index: 8780433 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0349. Min Range: -7.0349
Max Act: 6.3786. Min Act: -0.1700
Data Index: 2619234 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0349. Min Range: -7.0349
Max Act: 6.3474. Min Act: -0.1700
Data Index: 7092732 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19