Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5160 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0379. Min Range: -4.0379
Max Act: 4.0067. Min Act: -0.1700
Data Index: 5833142 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0379. Min Range: -4.0379
Max Act: 4.0379. Min Act: -0.1700
Data Index: 4119703 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.9129. Min Act: -0.1700
Data Index: 7307458 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.8816. Min Act: -0.1700
Data Index: 571611 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.9129. Min Act: -0.1700
Data Index: 7717550 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.8191. Min Act: -0.1700
Data Index: 4733949 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.8191. Min Act: -0.1700
Data Index: 4855150 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.8191. Min Act: -0.1700
Data Index: 4343038 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.7878. Min Act: -0.1700
Data Index: 3352962 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.7722. Min Act: -0.1700
Data Index: 7196400 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.7722. Min Act: -0.1700
Data Index: 3663262 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.7409. Min Act: -0.1700
Data Index: 8340992 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.7565. Min Act: -0.1700
Data Index: 5085689 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.7565. Min Act: -0.1700
Data Index: 7209683 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.7409. Min Act: -0.1700
Data Index: 720781 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.7096. Min Act: -0.1700
Data Index: 3731751 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.7096. Min Act: -0.1700
Data Index: 4487198 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.7096. Min Act: -0.1700
Data Index: 4016003 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.6783. Min Act: -0.1700
Data Index: 5690202 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0379. Min Range: -4.0379
Max Act: 3.6940. Min Act: -0.1700
Data Index: 2202022 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19