Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7567. Min Range: -4.7567
Max Act: 4.7567. Min Act: -0.1700
Data Index: 85997 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7567. Min Range: -4.7567
Max Act: 4.6317. Min Act: -0.1700
Data Index: 7755303 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7567. Min Range: -4.7567
Max Act: 4.6317. Min Act: -0.1700
Data Index: 7063850 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7567. Min Range: -4.7567
Max Act: 4.5692. Min Act: -0.1700
Data Index: 1114602 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7567. Min Range: -4.7567
Max Act: 4.5379. Min Act: -0.1700
Data Index: 1467088 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7567. Min Range: -4.7567
Max Act: 4.5692. Min Act: -0.1700
Data Index: 1638706 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7567. Min Range: -4.7567
Max Act: 4.5379. Min Act: -0.1700
Data Index: 7796408 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7567. Min Range: -4.7567
Max Act: 4.5067. Min Act: -0.1700
Data Index: 5516393 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7567. Min Range: -4.7567
Max Act: 4.5067. Min Act: -0.1700
Data Index: 1406318 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7567. Min Range: -4.7567
Max Act: 4.5067. Min Act: -0.1700
Data Index: 3960153 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7567. Min Range: -4.7567
Max Act: 4.5067. Min Act: -0.1700
Data Index: 303136 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7567. Min Range: -4.7567
Max Act: 4.4442. Min Act: -0.1700
Data Index: 925812 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7567. Min Range: -4.7567
Max Act: 4.4754. Min Act: -0.1700
Data Index: 7597578 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7567. Min Range: -4.7567
Max Act: 4.4754. Min Act: -0.1700
Data Index: 3212175 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7567. Min Range: -4.7567
Max Act: 4.4442. Min Act: -0.1700
Data Index: 3181985 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7567. Min Range: -4.7567
Max Act: 4.4442. Min Act: -0.1700
Data Index: 5318652 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7567. Min Range: -4.7567
Max Act: 4.4129. Min Act: -0.1700
Data Index: 7762706 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7567. Min Range: -4.7567
Max Act: 4.3817. Min Act: -0.1700
Data Index: 8156847 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7567. Min Range: -4.7567
Max Act: 4.3817. Min Act: -0.1700
Data Index: 5599150 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7567. Min Range: -4.7567
Max Act: 4.3817. Min Act: -0.1700
Data Index: 3109600 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19