Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5156 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7552. Min Range: -6.7552
Max Act: 6.7552. Min Act: -0.1700
Data Index: 505367 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7552. Min Range: -6.7552
Max Act: 6.6302. Min Act: -0.1700
Data Index: 1836460 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7552. Min Range: -6.7552
Max Act: 6.5989. Min Act: -0.1700
Data Index: 6230069 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7552. Min Range: -6.7552
Max Act: 6.6302. Min Act: -0.1700
Data Index: 5900903 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7552. Min Range: -6.7552
Max Act: 6.5989. Min Act: -0.1700
Data Index: 3540710 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7552. Min Range: -6.7552
Max Act: 6.5677. Min Act: -0.1700
Data Index: 8483187 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7552. Min Range: -6.7552
Max Act: 6.5677. Min Act: -0.1700
Data Index: 6967766 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7552. Min Range: -6.7552
Max Act: 6.5052. Min Act: -0.1700
Data Index: 4621049 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7552. Min Range: -6.7552
Max Act: 6.5364. Min Act: -0.1700
Data Index: 845733 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7552. Min Range: -6.7552
Max Act: 6.4739. Min Act: -0.1700
Data Index: 5814426 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7552. Min Range: -6.7552
Max Act: 6.4739. Min Act: -0.1700
Data Index: 346301 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7552. Min Range: -6.7552
Max Act: 6.5052. Min Act: -0.1700
Data Index: 6987379 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7552. Min Range: -6.7552
Max Act: 6.4427. Min Act: -0.1700
Data Index: 1011927 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7552. Min Range: -6.7552
Max Act: 6.4427. Min Act: -0.1700
Data Index: 542546 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7552. Min Range: -6.7552
Max Act: 6.3802. Min Act: -0.1700
Data Index: 1617160 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7552. Min Range: -6.7552
Max Act: 6.2864. Min Act: -0.1700
Data Index: 2455520 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7552. Min Range: -6.7552
Max Act: 6.2864. Min Act: -0.1700
Data Index: 6833278 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7552. Min Range: -6.7552
Max Act: 6.2552. Min Act: -0.1700
Data Index: 183964 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7552. Min Range: -6.7552
Max Act: 6.2864. Min Act: -0.1700
Data Index: 7896919 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7552. Min Range: -6.7552
Max Act: 6.2552. Min Act: -0.1700
Data Index: 4871140 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19