Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2809 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0382. Min Range: -6.0382
Max Act: 6.0382. Min Act: -0.1700
Data Index: 8611162 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0382. Min Range: -6.0382
Max Act: 5.9757. Min Act: -0.1700
Data Index: 799842 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0382. Min Range: -6.0382
Max Act: 5.9445. Min Act: -0.1700
Data Index: 4207441 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0382. Min Range: -6.0382
Max Act: 5.9445. Min Act: -0.1700
Data Index: 5273015 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0382. Min Range: -6.0382
Max Act: 5.9132. Min Act: -0.1700
Data Index: 4106779 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0382. Min Range: -6.0382
Max Act: 5.9132. Min Act: -0.1700
Data Index: 4088435 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0382. Min Range: -6.0382
Max Act: 5.9132. Min Act: -0.1700
Data Index: 816784 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0382. Min Range: -6.0382
Max Act: 5.8820. Min Act: -0.1700
Data Index: 1282261 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0382. Min Range: -6.0382
Max Act: 5.8820. Min Act: -0.1700
Data Index: 4088437 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0382. Min Range: -6.0382
Max Act: 5.8820. Min Act: -0.1700
Data Index: 3514150 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0382. Min Range: -6.0382
Max Act: 5.8195. Min Act: -0.1700
Data Index: 8651447 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0382. Min Range: -6.0382
Max Act: 5.8507. Min Act: -0.1700
Data Index: 3355318 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0382. Min Range: -6.0382
Max Act: 5.8195. Min Act: -0.1700
Data Index: 807540 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0382. Min Range: -6.0382
Max Act: 5.8195. Min Act: -0.1700
Data Index: 7418318 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0382. Min Range: -6.0382
Max Act: 5.7882. Min Act: -0.1700
Data Index: 4828930 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0382. Min Range: -6.0382
Max Act: 5.7882. Min Act: -0.1700
Data Index: 2795608 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0382. Min Range: -6.0382
Max Act: 5.7882. Min Act: -0.1700
Data Index: 2795609 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0382. Min Range: -6.0382
Max Act: 5.7882. Min Act: -0.1700
Data Index: 5941624 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0382. Min Range: -6.0382
Max Act: 5.7570. Min Act: -0.1700
Data Index: 2098153 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0382. Min Range: -6.0382
Max Act: 5.7570. Min Act: -0.1700
Data Index: 3240048 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19