Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4384 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7721. Min Range: -7.7721
Max Act: 7.7721. Min Act: -0.1700
Data Index: 2907315 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7721. Min Range: -7.7721
Max Act: 7.4283. Min Act: -0.1700
Data Index: 1514436 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7721. Min Range: -7.7721
Max Act: 7.3971. Min Act: -0.1700
Data Index: 7832866 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7721. Min Range: -7.7721
Max Act: 7.3033. Min Act: -0.1700
Data Index: 6677373 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7721. Min Range: -7.7721
Max Act: 7.2721. Min Act: -0.1700
Data Index: 4216731 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7721. Min Range: -7.7721
Max Act: 7.2408. Min Act: -0.1700
Data Index: 6794320 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7721. Min Range: -7.7721
Max Act: 7.1783. Min Act: -0.1700
Data Index: 3380769 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7721. Min Range: -7.7721
Max Act: 7.2408. Min Act: -0.1700
Data Index: 4075457 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7721. Min Range: -7.7721
Max Act: 7.2096. Min Act: -0.1700
Data Index: 5205097 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7721. Min Range: -7.7721
Max Act: 7.1783. Min Act: -0.1700
Data Index: 2275174 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7721. Min Range: -7.7721
Max Act: 7.1158. Min Act: -0.1700
Data Index: 2724417 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7721. Min Range: -7.7721
Max Act: 7.1158. Min Act: -0.1700
Data Index: 5886587 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7721. Min Range: -7.7721
Max Act: 7.0846. Min Act: -0.1700
Data Index: 7412579 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7721. Min Range: -7.7721
Max Act: 7.1158. Min Act: -0.1700
Data Index: 29895 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7721. Min Range: -7.7721
Max Act: 7.0533. Min Act: -0.1700
Data Index: 4354138 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7721. Min Range: -7.7721
Max Act: 7.0221. Min Act: -0.1700
Data Index: 8184511 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7721. Min Range: -7.7721
Max Act: 7.0221. Min Act: -0.1700
Data Index: 8554583 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7721. Min Range: -7.7721
Max Act: 6.9908. Min Act: -0.1700
Data Index: 5585751 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7721. Min Range: -7.7721
Max Act: 7.0221. Min Act: -0.1700
Data Index: 8501296 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7721. Min Range: -7.7721
Max Act: 6.9596. Min Act: -0.1700
Data Index: 6104720 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19