Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4002 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9565. Min Range: -4.9565
Max Act: 4.9565. Min Act: -0.1700
Data Index: 7121293 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9565. Min Range: -4.9565
Max Act: 4.8002. Min Act: -0.1700
Data Index: 7972963 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9565. Min Range: -4.9565
Max Act: 4.7377. Min Act: -0.1700
Data Index: 2921696 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9565. Min Range: -4.9565
Max Act: 4.6752. Min Act: -0.1700
Data Index: 5696832 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9565. Min Range: -4.9565
Max Act: 4.6440. Min Act: -0.1700
Data Index: 1022417 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9565. Min Range: -4.9565
Max Act: 4.6440. Min Act: -0.1700
Data Index: 2451816 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9565. Min Range: -4.9565
Max Act: 4.6127. Min Act: -0.1700
Data Index: 268336 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9565. Min Range: -4.9565
Max Act: 4.6127. Min Act: -0.1700
Data Index: 1545495 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9565. Min Range: -4.9565
Max Act: 4.5502. Min Act: -0.1700
Data Index: 835205 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9565. Min Range: -4.9565
Max Act: 4.5815. Min Act: -0.1700
Data Index: 268337 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9565. Min Range: -4.9565
Max Act: 4.5815. Min Act: -0.1700
Data Index: 2570061 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9565. Min Range: -4.9565
Max Act: 4.5815. Min Act: -0.1700
Data Index: 1086898 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9565. Min Range: -4.9565
Max Act: 4.5815. Min Act: -0.1700
Data Index: 2430918 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9565. Min Range: -4.9565
Max Act: 4.5815. Min Act: -0.1700
Data Index: 8027125 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9565. Min Range: -4.9565
Max Act: 4.5815. Min Act: -0.1700
Data Index: 1505083 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9565. Min Range: -4.9565
Max Act: 4.5502. Min Act: -0.1700
Data Index: 3351832 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9565. Min Range: -4.9565
Max Act: 4.5502. Min Act: -0.1700
Data Index: 4063876 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9565. Min Range: -4.9565
Max Act: 4.5502. Min Act: -0.1700
Data Index: 2521716 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9565. Min Range: -4.9565
Max Act: 4.5502. Min Act: -0.1700
Data Index: 7548724 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9565. Min Range: -4.9565
Max Act: 4.5190. Min Act: -0.1700
Data Index: 4224078 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19