Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5354 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3382. Min Range: -6.3382
Max Act: 6.3382. Min Act: -0.1700
Data Index: 7519255 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3382. Min Range: -6.3382
Max Act: 6.3382. Min Act: -0.1700
Data Index: 2514810 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3382. Min Range: -6.3382
Max Act: 6.1820. Min Act: -0.1700
Data Index: 3653512 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3382. Min Range: -6.3382
Max Act: 6.0570. Min Act: -0.1700
Data Index: 2771833 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3382. Min Range: -6.3382
Max Act: 6.0570. Min Act: -0.1700
Data Index: 3766041 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3382. Min Range: -6.3382
Max Act: 6.0257. Min Act: -0.1700
Data Index: 3573001 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3382. Min Range: -6.3382
Max Act: 5.9945. Min Act: -0.1700
Data Index: 5240688 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3382. Min Range: -6.3382
Max Act: 5.9945. Min Act: -0.1700
Data Index: 3624696 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3382. Min Range: -6.3382
Max Act: 5.9945. Min Act: -0.1700
Data Index: 7936250 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3382. Min Range: -6.3382
Max Act: 5.9632. Min Act: -0.1700
Data Index: 4798747 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3382. Min Range: -6.3382
Max Act: 5.9632. Min Act: -0.1700
Data Index: 2199769 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3382. Min Range: -6.3382
Max Act: 5.8695. Min Act: -0.1700
Data Index: 833914 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3382. Min Range: -6.3382
Max Act: 5.8695. Min Act: -0.1700
Data Index: 3286521 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3382. Min Range: -6.3382
Max Act: 5.8382. Min Act: -0.1700
Data Index: 7068308 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3382. Min Range: -6.3382
Max Act: 5.8070. Min Act: -0.1700
Data Index: 674301 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3382. Min Range: -6.3382
Max Act: 5.7757. Min Act: -0.1700
Data Index: 8725598 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3382. Min Range: -6.3382
Max Act: 5.8070. Min Act: -0.1700
Data Index: 8174628 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3382. Min Range: -6.3382
Max Act: 5.7757. Min Act: -0.1700
Data Index: 2068011 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3382. Min Range: -6.3382
Max Act: 5.7757. Min Act: -0.1700
Data Index: 1077117 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3382. Min Range: -6.3382
Max Act: 5.8070. Min Act: -0.1700
Data Index: 3065641 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19