Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2748 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.9386. Min Act: -0.1700
Data Index: 3867752 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.9386. Min Act: -0.1700
Data Index: 2205899 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.9074. Min Act: -0.1700
Data Index: 903370 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.9074. Min Act: -0.1700
Data Index: 5263179 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.8449. Min Act: -0.1700
Data Index: 2440634 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.7824. Min Act: -0.1700
Data Index: 8083917 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.7824. Min Act: -0.1700
Data Index: 3146855 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.7511. Min Act: -0.1700
Data Index: 3628732 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.6886. Min Act: -0.1700
Data Index: 1930892 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.6886. Min Act: -0.1700
Data Index: 187434 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.6574. Min Act: -0.1700
Data Index: 7737729 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.6574. Min Act: -0.1700
Data Index: 5126994 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.6261. Min Act: -0.1700
Data Index: 7032463 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.5949. Min Act: -0.1700
Data Index: 7093482 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.5949. Min Act: -0.1700
Data Index: 7955566 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.5636. Min Act: -0.1700
Data Index: 6473922 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.5636. Min Act: -0.1700
Data Index: 6859135 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.5636. Min Act: -0.1700
Data Index: 6388830 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.5324. Min Act: -0.1700
Data Index: 2144176 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.5636. Min Act: -0.1700
Data Index: 8732702 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19