Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1550 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.7856. Min Act: -0.1700
Data Index: 8724169 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.6291. Min Act: -0.1700
Data Index: 5621337 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.6135. Min Act: -0.1700
Data Index: 6991689 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5978. Min Act: -0.1700
Data Index: 5285185 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5665. Min Act: -0.1700
Data Index: 5769764 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5665. Min Act: -0.1700
Data Index: 7334023 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5509. Min Act: -0.1700
Data Index: 3809963 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5352. Min Act: -0.1700
Data Index: 8249360 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5509. Min Act: -0.1700
Data Index: 6754957 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5352. Min Act: -0.1700
Data Index: 3448842 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5352. Min Act: -0.1700
Data Index: 2909179 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5509. Min Act: -0.1700
Data Index: 7915699 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5195. Min Act: -0.1700
Data Index: 8113337 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5195. Min Act: -0.1700
Data Index: 5916323 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5195. Min Act: -0.1700
Data Index: 5062650 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5039. Min Act: -0.1700
Data Index: 5439145 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5039. Min Act: -0.1700
Data Index: 4658464 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.4882. Min Act: -0.1700
Data Index: 8679031 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.4726. Min Act: -0.1700
Data Index: 5915034 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.4726. Min Act: -0.1700
Data Index: 1843035 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19