Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3268 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7976. Min Range: -6.7976
Max Act: 6.7976. Min Act: -0.1700
Data Index: 4173052 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7976. Min Range: -6.7976
Max Act: 6.7663. Min Act: -0.1700
Data Index: 2653378 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7976. Min Range: -6.7976
Max Act: 6.7038. Min Act: -0.1700
Data Index: 6988994 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7976. Min Range: -6.7976
Max Act: 6.6726. Min Act: -0.1700
Data Index: 4222124 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7976. Min Range: -6.7976
Max Act: 6.6413. Min Act: -0.1700
Data Index: 4816086 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7976. Min Range: -6.7976
Max Act: 6.6101. Min Act: -0.1700
Data Index: 5448242 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7976. Min Range: -6.7976
Max Act: 6.6101. Min Act: -0.1700
Data Index: 8658755 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7976. Min Range: -6.7976
Max Act: 6.5788. Min Act: -0.1700
Data Index: 3484945 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7976. Min Range: -6.7976
Max Act: 6.5476. Min Act: -0.1700
Data Index: 6864897 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7976. Min Range: -6.7976
Max Act: 6.4851. Min Act: -0.1700
Data Index: 8121622 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7976. Min Range: -6.7976
Max Act: 6.4226. Min Act: -0.1700
Data Index: 4707612 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7976. Min Range: -6.7976
Max Act: 6.3913. Min Act: -0.1700
Data Index: 3831515 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7976. Min Range: -6.7976
Max Act: 6.4226. Min Act: -0.1700
Data Index: 7997477 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7976. Min Range: -6.7976
Max Act: 6.3288. Min Act: -0.1700
Data Index: 1689655 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7976. Min Range: -6.7976
Max Act: 6.3288. Min Act: -0.1700
Data Index: 772270 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7976. Min Range: -6.7976
Max Act: 6.2976. Min Act: -0.1700
Data Index: 8453826 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7976. Min Range: -6.7976
Max Act: 6.2976. Min Act: -0.1700
Data Index: 4952737 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7976. Min Range: -6.7976
Max Act: 6.2976. Min Act: -0.1700
Data Index: 6919848 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7976. Min Range: -6.7976
Max Act: 6.2663. Min Act: -0.1700
Data Index: 4374734 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7976. Min Range: -6.7976
Max Act: 6.2663. Min Act: -0.1700
Data Index: 6493284 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19