Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4651 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8156. Min Range: -5.8156
Max Act: 5.8156. Min Act: -0.1700
Data Index: 4572382 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8156. Min Range: -5.8156
Max Act: 5.7531. Min Act: -0.1700
Data Index: 4304634 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8156. Min Range: -5.8156
Max Act: 5.6593. Min Act: -0.1700
Data Index: 8446171 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8156. Min Range: -5.8156
Max Act: 5.5968. Min Act: -0.1700
Data Index: 7980916 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8156. Min Range: -5.8156
Max Act: 5.5656. Min Act: -0.1700
Data Index: 4812679 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8156. Min Range: -5.8156
Max Act: 5.5031. Min Act: -0.1700
Data Index: 2593628 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8156. Min Range: -5.8156
Max Act: 5.3468. Min Act: -0.1700
Data Index: 4034945 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8156. Min Range: -5.8156
Max Act: 5.3156. Min Act: -0.1700
Data Index: 7578102 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8156. Min Range: -5.8156
Max Act: 5.2531. Min Act: -0.1700
Data Index: 173630 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8156. Min Range: -5.8156
Max Act: 5.2531. Min Act: -0.1700
Data Index: 3793476 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8156. Min Range: -5.8156
Max Act: 5.2531. Min Act: -0.1700
Data Index: 761534 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8156. Min Range: -5.8156
Max Act: 5.2531. Min Act: -0.1700
Data Index: 2975445 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8156. Min Range: -5.8156
Max Act: 5.2531. Min Act: -0.1700
Data Index: 7529742 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8156. Min Range: -5.8156
Max Act: 5.1906. Min Act: -0.1700
Data Index: 2257102 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8156. Min Range: -5.8156
Max Act: 5.2218. Min Act: -0.1700
Data Index: 8811846 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8156. Min Range: -5.8156
Max Act: 5.2218. Min Act: -0.1700
Data Index: 6632663 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8156. Min Range: -5.8156
Max Act: 5.1906. Min Act: -0.1700
Data Index: 6607963 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8156. Min Range: -5.8156
Max Act: 5.1906. Min Act: -0.1700
Data Index: 148597 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8156. Min Range: -5.8156
Max Act: 5.1906. Min Act: -0.1700
Data Index: 5735371 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8156. Min Range: -5.8156
Max Act: 5.1593. Min Act: -0.1700
Data Index: 990933 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19