Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4636 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0152. Min Range: -5.0152
Max Act: 5.0152. Min Act: -0.1700
Data Index: 966382 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0152. Min Range: -5.0152
Max Act: 4.8589. Min Act: -0.1700
Data Index: 6258415 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0152. Min Range: -5.0152
Max Act: 4.8277. Min Act: -0.1700
Data Index: 4602804 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0152. Min Range: -5.0152
Max Act: 4.8277. Min Act: -0.1700
Data Index: 580956 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0152. Min Range: -5.0152
Max Act: 4.8589. Min Act: -0.1700
Data Index: 4191239 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0152. Min Range: -5.0152
Max Act: 4.7964. Min Act: -0.1700
Data Index: 5424856 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0152. Min Range: -5.0152
Max Act: 4.7964. Min Act: -0.1700
Data Index: 2801917 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0152. Min Range: -5.0152
Max Act: 4.7652. Min Act: -0.1700
Data Index: 381790 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0152. Min Range: -5.0152
Max Act: 4.7964. Min Act: -0.1700
Data Index: 3707250 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0152. Min Range: -5.0152
Max Act: 4.7652. Min Act: -0.1700
Data Index: 2010128 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0152. Min Range: -5.0152
Max Act: 4.7339. Min Act: -0.1700
Data Index: 3352815 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0152. Min Range: -5.0152
Max Act: 4.7652. Min Act: -0.1700
Data Index: 6679605 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0152. Min Range: -5.0152
Max Act: 4.7652. Min Act: -0.1700
Data Index: 479115 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0152. Min Range: -5.0152
Max Act: 4.7652. Min Act: -0.1700
Data Index: 4098058 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0152. Min Range: -5.0152
Max Act: 4.7652. Min Act: -0.1700
Data Index: 5778106 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0152. Min Range: -5.0152
Max Act: 4.7339. Min Act: -0.1700
Data Index: 2549616 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0152. Min Range: -5.0152
Max Act: 4.7339. Min Act: -0.1700
Data Index: 3849432 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0152. Min Range: -5.0152
Max Act: 4.7339. Min Act: -0.1700
Data Index: 4866504 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0152. Min Range: -5.0152
Max Act: 4.7339. Min Act: -0.1700
Data Index: 5429752 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0152. Min Range: -5.0152
Max Act: 4.7339. Min Act: -0.1700
Data Index: 5424857 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19