Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5110 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3817. Min Range: -5.3817
Max Act: 5.3817. Min Act: -0.1700
Data Index: 3786445 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3817. Min Range: -5.3817
Max Act: 5.3505. Min Act: -0.1700
Data Index: 3762130 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3817. Min Range: -5.3817
Max Act: 5.1630. Min Act: -0.1700
Data Index: 905049 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3817. Min Range: -5.3817
Max Act: 5.1005. Min Act: -0.1700
Data Index: 3762129 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3817. Min Range: -5.3817
Max Act: 5.0380. Min Act: -0.1700
Data Index: 2647170 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3817. Min Range: -5.3817
Max Act: 5.0692. Min Act: -0.1700
Data Index: 1576585 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3817. Min Range: -5.3817
Max Act: 5.1005. Min Act: -0.1700
Data Index: 1147370 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3817. Min Range: -5.3817
Max Act: 5.0692. Min Act: -0.1700
Data Index: 3428575 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3817. Min Range: -5.3817
Max Act: 5.0380. Min Act: -0.1700
Data Index: 2869184 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3817. Min Range: -5.3817
Max Act: 5.0380. Min Act: -0.1700
Data Index: 7811603 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3817. Min Range: -5.3817
Max Act: 5.0067. Min Act: -0.1700
Data Index: 3866122 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3817. Min Range: -5.3817
Max Act: 5.0067. Min Act: -0.1700
Data Index: 7704961 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3817. Min Range: -5.3817
Max Act: 5.0067. Min Act: -0.1700
Data Index: 1722614 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3817. Min Range: -5.3817
Max Act: 5.0067. Min Act: -0.1700
Data Index: 6031380 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3817. Min Range: -5.3817
Max Act: 5.0067. Min Act: -0.1700
Data Index: 4803526 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3817. Min Range: -5.3817
Max Act: 4.9755. Min Act: -0.1700
Data Index: 4364141 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3817. Min Range: -5.3817
Max Act: 4.9755. Min Act: -0.1700
Data Index: 2258843 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3817. Min Range: -5.3817
Max Act: 4.9442. Min Act: -0.1700
Data Index: 6746382 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3817. Min Range: -5.3817
Max Act: 4.9442. Min Act: -0.1700
Data Index: 1147371 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3817. Min Range: -5.3817
Max Act: 4.9442. Min Act: -0.1700
Data Index: 3339996 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19