Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 659 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9158. Min Range: -4.9158
Max Act: 4.9158. Min Act: -0.1700
Data Index: 4016219 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9158. Min Range: -4.9158
Max Act: 4.8221. Min Act: -0.1700
Data Index: 3940960 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9158. Min Range: -4.9158
Max Act: 4.8221. Min Act: -0.1700
Data Index: 2567229 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9158. Min Range: -4.9158
Max Act: 4.7596. Min Act: -0.1700
Data Index: 5128011 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9158. Min Range: -4.9158
Max Act: 4.7596. Min Act: -0.1700
Data Index: 136854 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9158. Min Range: -4.9158
Max Act: 4.7596. Min Act: -0.1700
Data Index: 6714198 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9158. Min Range: -4.9158
Max Act: 4.7283. Min Act: -0.1700
Data Index: 4016217 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9158. Min Range: -4.9158
Max Act: 4.6971. Min Act: -0.1700
Data Index: 8380464 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9158. Min Range: -4.9158
Max Act: 4.6971. Min Act: -0.1700
Data Index: 5713203 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9158. Min Range: -4.9158
Max Act: 4.6971. Min Act: -0.1700
Data Index: 4016218 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9158. Min Range: -4.9158
Max Act: 4.6658. Min Act: -0.1700
Data Index: 7716598 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9158. Min Range: -4.9158
Max Act: 4.6658. Min Act: -0.1700
Data Index: 7955875 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9158. Min Range: -4.9158
Max Act: 4.6033. Min Act: -0.1700
Data Index: 7955876 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9158. Min Range: -4.9158
Max Act: 4.5408. Min Act: -0.1700
Data Index: 2976507 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9158. Min Range: -4.9158
Max Act: 4.5408. Min Act: -0.1700
Data Index: 3010348 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9158. Min Range: -4.9158
Max Act: 4.5408. Min Act: -0.1700
Data Index: 1960914 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9158. Min Range: -4.9158
Max Act: 4.5096. Min Act: -0.1700
Data Index: 7792908 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9158. Min Range: -4.9158
Max Act: 4.5096. Min Act: -0.1700
Data Index: 7900403 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9158. Min Range: -4.9158
Max Act: 4.5096. Min Act: -0.1700
Data Index: 1763776 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9158. Min Range: -4.9158
Max Act: 4.4783. Min Act: -0.1700
Data Index: 7651008 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19