Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1196 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.9503. Min Act: -0.1700
Data Index: 5156514 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.8565. Min Act: -0.1700
Data Index: 560309 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.8565. Min Act: -0.1700
Data Index: 2080791 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.8565. Min Act: -0.1700
Data Index: 8799652 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.8565. Min Act: -0.1700
Data Index: 8799653 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.8252. Min Act: -0.1700
Data Index: 2253621 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.7939. Min Act: -0.1700
Data Index: 560310 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.7939. Min Act: -0.1700
Data Index: 6424192 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.7939. Min Act: -0.1700
Data Index: 4786346 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.7939. Min Act: -0.1700
Data Index: 1502912 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.7939. Min Act: -0.1700
Data Index: 4863402 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.7626. Min Act: -0.1700
Data Index: 5916242 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.7314. Min Act: -0.1700
Data Index: 2071291 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.7314. Min Act: -0.1700
Data Index: 1010643 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.7314. Min Act: -0.1700
Data Index: 7088062 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.7001. Min Act: -0.1700
Data Index: 4276492 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.7001. Min Act: -0.1700
Data Index: 4276861 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.7001. Min Act: -0.1700
Data Index: 6878664 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.7314. Min Act: -0.1700
Data Index: 4816345 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.7001. Min Act: -0.1700
Data Index: 951726 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19