Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4376 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5439. Min Range: -5.5439
Max Act: 5.5439. Min Act: -0.1700
Data Index: 8204288 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5439. Min Range: -5.5439
Max Act: 5.4814. Min Act: -0.1700
Data Index: 4073116 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5439. Min Range: -5.5439
Max Act: 5.3564. Min Act: -0.1700
Data Index: 7985970 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5439. Min Range: -5.5439
Max Act: 5.3564. Min Act: -0.1699
Data Index: 8433607 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5439. Min Range: -5.5439
Max Act: 5.3251. Min Act: -0.1700
Data Index: 3014045 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5439. Min Range: -5.5439
Max Act: 5.2626. Min Act: -0.1700
Data Index: 1565 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5439. Min Range: -5.5439
Max Act: 5.2626. Min Act: -0.1700
Data Index: 528605 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5439. Min Range: -5.5439
Max Act: 5.2626. Min Act: -0.1700
Data Index: 8433616 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5439. Min Range: -5.5439
Max Act: 5.2626. Min Act: -0.1700
Data Index: 316471 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5439. Min Range: -5.5439
Max Act: 5.2314. Min Act: -0.1700
Data Index: 2089286 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5439. Min Range: -5.5439
Max Act: 5.2314. Min Act: -0.1700
Data Index: 2496068 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5439. Min Range: -5.5439
Max Act: 5.2314. Min Act: -0.1700
Data Index: 1766601 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5439. Min Range: -5.5439
Max Act: 5.2314. Min Act: -0.1700
Data Index: 7868506 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5439. Min Range: -5.5439
Max Act: 5.2314. Min Act: -0.1700
Data Index: 6490105 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5439. Min Range: -5.5439
Max Act: 5.2314. Min Act: -0.1700
Data Index: 6330748 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5439. Min Range: -5.5439
Max Act: 5.2314. Min Act: -0.1700
Data Index: 4476367 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5439. Min Range: -5.5439
Max Act: 5.2001. Min Act: -0.1700
Data Index: 3732249 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5439. Min Range: -5.5439
Max Act: 5.2001. Min Act: -0.1700
Data Index: 2209873 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5439. Min Range: -5.5439
Max Act: 5.2001. Min Act: -0.1700
Data Index: 5268691 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5439. Min Range: -5.5439
Max Act: 5.2001. Min Act: -0.1700
Data Index: 316480 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19