Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4864 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4157. Min Range: -4.4157
Max Act: 4.4157. Min Act: -0.1700
Data Index: 8626479 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4157. Min Range: -4.4157
Max Act: 4.3845. Min Act: -0.1700
Data Index: 6346417 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4157. Min Range: -4.4157
Max Act: 4.2907. Min Act: -0.1700
Data Index: 4540850 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4157. Min Range: -4.4157
Max Act: 4.2595. Min Act: -0.1700
Data Index: 1063377 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4157. Min Range: -4.4157
Max Act: 4.1657. Min Act: -0.1700
Data Index: 4024872 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4157. Min Range: -4.4157
Max Act: 4.1970. Min Act: -0.1700
Data Index: 1898574 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4157. Min Range: -4.4157
Max Act: 4.1345. Min Act: -0.1700
Data Index: 3395150 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4157. Min Range: -4.4157
Max Act: 4.1032. Min Act: -0.1700
Data Index: 3532610 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4157. Min Range: -4.4157
Max Act: 4.1032. Min Act: -0.1700
Data Index: 8765220 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4157. Min Range: -4.4157
Max Act: 4.1032. Min Act: -0.1700
Data Index: 1442052 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4157. Min Range: -4.4157
Max Act: 4.0720. Min Act: -0.1700
Data Index: 3974887 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4157. Min Range: -4.4157
Max Act: 4.0720. Min Act: -0.1700
Data Index: 440090 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4157. Min Range: -4.4157
Max Act: 4.0094. Min Act: -0.1700
Data Index: 6642067 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4157. Min Range: -4.4157
Max Act: 4.0094. Min Act: -0.1700
Data Index: 7054730 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4157. Min Range: -4.4157
Max Act: 4.0094. Min Act: -0.1700
Data Index: 7931517 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4157. Min Range: -4.4157
Max Act: 4.0094. Min Act: -0.1700
Data Index: 7971630 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4157. Min Range: -4.4157
Max Act: 3.9782. Min Act: -0.1700
Data Index: 3766853 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4157. Min Range: -4.4157
Max Act: 4.0094. Min Act: -0.1700
Data Index: 6421580 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4157. Min Range: -4.4157
Max Act: 4.0094. Min Act: -0.1700
Data Index: 6952028 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4157. Min Range: -4.4157
Max Act: 4.0094. Min Act: -0.1700
Data Index: 1783864 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19