Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4396 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4566. Min Range: -6.4566
Max Act: 6.4566. Min Act: -0.1700
Data Index: 2542330 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4566. Min Range: -6.4566
Max Act: 6.3628. Min Act: -0.1700
Data Index: 4876958 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4566. Min Range: -6.4566
Max Act: 6.1441. Min Act: -0.1700
Data Index: 8291675 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4566. Min Range: -6.4566
Max Act: 6.0816. Min Act: -0.1700
Data Index: 6885744 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4566. Min Range: -6.4566
Max Act: 6.0503. Min Act: -0.1700
Data Index: 1226417 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4566. Min Range: -6.4566
Max Act: 5.9566. Min Act: -0.1700
Data Index: 5628873 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4566. Min Range: -6.4566
Max Act: 5.9253. Min Act: -0.1700
Data Index: 2454011 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4566. Min Range: -6.4566
Max Act: 5.8003. Min Act: -0.1700
Data Index: 6926428 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4566. Min Range: -6.4566
Max Act: 5.8003. Min Act: -0.1700
Data Index: 7264907 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4566. Min Range: -6.4566
Max Act: 5.8003. Min Act: -0.1700
Data Index: 3427512 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4566. Min Range: -6.4566
Max Act: 5.8003. Min Act: -0.1700
Data Index: 2480112 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4566. Min Range: -6.4566
Max Act: 5.8003. Min Act: -0.1700
Data Index: 2528274 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4566. Min Range: -6.4566
Max Act: 5.7691. Min Act: -0.1700
Data Index: 7547931 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4566. Min Range: -6.4566
Max Act: 5.7378. Min Act: -0.1700
Data Index: 4766739 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4566. Min Range: -6.4566
Max Act: 5.8003. Min Act: -0.1700
Data Index: 3064814 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4566. Min Range: -6.4566
Max Act: 5.7378. Min Act: -0.1700
Data Index: 360972 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4566. Min Range: -6.4566
Max Act: 5.7378. Min Act: -0.1700
Data Index: 7668778 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4566. Min Range: -6.4566
Max Act: 5.6753. Min Act: -0.1700
Data Index: 7076481 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4566. Min Range: -6.4566
Max Act: 5.7066. Min Act: -0.1700
Data Index: 6247131 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4566. Min Range: -6.4566
Max Act: 5.6753. Min Act: -0.1700
Data Index: 3435144 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19