Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3635 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6507. Min Range: -6.6507
Max Act: 6.6507. Min Act: -0.1700
Data Index: 3081387 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6507. Min Range: -6.6507
Max Act: 6.3382. Min Act: -0.1700
Data Index: 4253216 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6507. Min Range: -6.6507
Max Act: 6.1507. Min Act: -0.1700
Data Index: 900845 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6507. Min Range: -6.6507
Max Act: 6.1507. Min Act: -0.1700
Data Index: 5439379 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6507. Min Range: -6.6507
Max Act: 6.1195. Min Act: -0.1700
Data Index: 3022606 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6507. Min Range: -6.6507
Max Act: 6.0882. Min Act: -0.1700
Data Index: 3730691 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6507. Min Range: -6.6507
Max Act: 6.0570. Min Act: -0.1700
Data Index: 2348851 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6507. Min Range: -6.6507
Max Act: 6.0570. Min Act: -0.1700
Data Index: 2806546 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6507. Min Range: -6.6507
Max Act: 6.0257. Min Act: -0.1700
Data Index: 7370851 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6507. Min Range: -6.6507
Max Act: 5.9945. Min Act: -0.1700
Data Index: 8783910 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6507. Min Range: -6.6507
Max Act: 5.9945. Min Act: -0.1700
Data Index: 1509669 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6507. Min Range: -6.6507
Max Act: 5.9945. Min Act: -0.1700
Data Index: 2394153 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6507. Min Range: -6.6507
Max Act: 5.9320. Min Act: -0.1700
Data Index: 277310 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6507. Min Range: -6.6507
Max Act: 5.9632. Min Act: -0.1700
Data Index: 3205869 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6507. Min Range: -6.6507
Max Act: 5.9632. Min Act: -0.1700
Data Index: 910836 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6507. Min Range: -6.6507
Max Act: 5.9632. Min Act: -0.1700
Data Index: 1056667 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6507. Min Range: -6.6507
Max Act: 5.9632. Min Act: -0.1700
Data Index: 7033731 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6507. Min Range: -6.6507
Max Act: 5.9632. Min Act: -0.1700
Data Index: 515281 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6507. Min Range: -6.6507
Max Act: 5.9320. Min Act: -0.1700
Data Index: 3386091 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6507. Min Range: -6.6507
Max Act: 5.9632. Min Act: -0.1700
Data Index: 936714 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19