Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 266 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8856. Min Range: -4.8856
Max Act: 4.8856. Min Act: -0.1700
Data Index: 1213694 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8856. Min Range: -4.8856
Max Act: 4.6981. Min Act: -0.1700
Data Index: 5947078 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8856. Min Range: -4.8856
Max Act: 4.5731. Min Act: -0.1700
Data Index: 2019499 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8856. Min Range: -4.8856
Max Act: 4.6044. Min Act: -0.1700
Data Index: 1310054 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8856. Min Range: -4.8856
Max Act: 4.6044. Min Act: -0.1700
Data Index: 5109522 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8856. Min Range: -4.8856
Max Act: 4.5106. Min Act: -0.1700
Data Index: 6706824 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8856. Min Range: -4.8856
Max Act: 4.4793. Min Act: -0.1700
Data Index: 617466 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8856. Min Range: -4.8856
Max Act: 4.4793. Min Act: -0.1700
Data Index: 8596206 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8856. Min Range: -4.8856
Max Act: 4.3543. Min Act: -0.1700
Data Index: 8033718 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8856. Min Range: -4.8856
Max Act: 4.3856. Min Act: -0.1700
Data Index: 396925 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8856. Min Range: -4.8856
Max Act: 4.3856. Min Act: -0.1700
Data Index: 3232130 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8856. Min Range: -4.8856
Max Act: 4.3543. Min Act: -0.1700
Data Index: 8828654 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8856. Min Range: -4.8856
Max Act: 4.3231. Min Act: -0.1700
Data Index: 7810967 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8856. Min Range: -4.8856
Max Act: 4.2918. Min Act: -0.1700
Data Index: 7819795 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8856. Min Range: -4.8856
Max Act: 4.3543. Min Act: -0.1700
Data Index: 7127495 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8856. Min Range: -4.8856
Max Act: 4.3231. Min Act: -0.1700
Data Index: 3448234 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8856. Min Range: -4.8856
Max Act: 4.3231. Min Act: -0.1700
Data Index: 6159871 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8856. Min Range: -4.8856
Max Act: 4.2918. Min Act: -0.1700
Data Index: 6047267 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8856. Min Range: -4.8856
Max Act: 4.2918. Min Act: -0.1700
Data Index: 6427009 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8856. Min Range: -4.8856
Max Act: 4.2918. Min Act: -0.1700
Data Index: 7355190 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19