Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2883 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.6075. Min Act: -0.1700
Data Index: 8719796 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.6075. Min Act: -0.1700
Data Index: 2287691 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.5450. Min Act: -0.1700
Data Index: 1617318 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.5450. Min Act: -0.1700
Data Index: 2590763 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.5450. Min Act: -0.1700
Data Index: 798487 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.5138. Min Act: -0.1700
Data Index: 628995 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.4825. Min Act: -0.1700
Data Index: 798499 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.4513. Min Act: -0.1700
Data Index: 5208100 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.4200. Min Act: -0.1700
Data Index: 3846534 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.4513. Min Act: -0.1700
Data Index: 5712868 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.4200. Min Act: -0.1700
Data Index: 5208101 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.4200. Min Act: -0.1700
Data Index: 2590762 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.3888. Min Act: -0.1700
Data Index: 798490 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.3888. Min Act: -0.1700
Data Index: 1765641 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.3575. Min Act: -0.1700
Data Index: 6484669 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.3575. Min Act: -0.1700
Data Index: 5392192 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.3575. Min Act: -0.1700
Data Index: 236604 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.3263. Min Act: -0.1700
Data Index: 3118770 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.3575. Min Act: -0.1700
Data Index: 6683679 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.3575. Min Act: -0.1700
Data Index: 8470411 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19