Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3018 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0244. Min Range: -5.0244
Max Act: 5.0244. Min Act: -0.1700
Data Index: 547668 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0244. Min Range: -5.0244
Max Act: 4.8994. Min Act: -0.1700
Data Index: 6504401 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0244. Min Range: -5.0244
Max Act: 4.8681. Min Act: -0.1700
Data Index: 1365814 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0244. Min Range: -5.0244
Max Act: 4.7744. Min Act: -0.1700
Data Index: 5552964 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0244. Min Range: -5.0244
Max Act: 4.7119. Min Act: -0.1700
Data Index: 6086931 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0244. Min Range: -5.0244
Max Act: 4.7431. Min Act: -0.1700
Data Index: 8510058 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0244. Min Range: -5.0244
Max Act: 4.7431. Min Act: -0.1700
Data Index: 5552984 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0244. Min Range: -5.0244
Max Act: 4.6806. Min Act: -0.1700
Data Index: 2289475 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0244. Min Range: -5.0244
Max Act: 4.6494. Min Act: -0.1700
Data Index: 7154404 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0244. Min Range: -5.0244
Max Act: 4.6494. Min Act: -0.1700
Data Index: 7251287 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0244. Min Range: -5.0244
Max Act: 4.6494. Min Act: -0.1700
Data Index: 7399566 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0244. Min Range: -5.0244
Max Act: 4.6494. Min Act: -0.1700
Data Index: 7988722 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0244. Min Range: -5.0244
Max Act: 4.6494. Min Act: -0.1700
Data Index: 4150967 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0244. Min Range: -5.0244
Max Act: 4.6181. Min Act: -0.1700
Data Index: 6958364 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0244. Min Range: -5.0244
Max Act: 4.6181. Min Act: -0.1700
Data Index: 232463 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0244. Min Range: -5.0244
Max Act: 4.6181. Min Act: -0.1700
Data Index: 2406048 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0244. Min Range: -5.0244
Max Act: 4.6181. Min Act: -0.1700
Data Index: 3220627 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0244. Min Range: -5.0244
Max Act: 4.6181. Min Act: -0.1700
Data Index: 5896386 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0244. Min Range: -5.0244
Max Act: 4.6181. Min Act: -0.1700
Data Index: 1521181 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0244. Min Range: -5.0244
Max Act: 4.5868. Min Act: -0.1700
Data Index: 6893798 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19