Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3887 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5979. Min Range: -8.5979
Max Act: 8.5979. Min Act: -0.1700
Data Index: 1723069 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5979. Min Range: -8.5979
Max Act: 8.4729. Min Act: -0.1700
Data Index: 6533754 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5979. Min Range: -8.5979
Max Act: 8.4104. Min Act: -0.1700
Data Index: 280117 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5979. Min Range: -8.5979
Max Act: 8.4104. Min Act: -0.1700
Data Index: 3970211 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5979. Min Range: -8.5979
Max Act: 8.3479. Min Act: -0.1700
Data Index: 3171675 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5979. Min Range: -8.5979
Max Act: 8.2854. Min Act: -0.1700
Data Index: 7312913 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5979. Min Range: -8.5979
Max Act: 8.2854. Min Act: -0.1700
Data Index: 6061087 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5979. Min Range: -8.5979
Max Act: 8.2229. Min Act: -0.1700
Data Index: 1120494 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5979. Min Range: -8.5979
Max Act: 8.1604. Min Act: -0.1700
Data Index: 7639559 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5979. Min Range: -8.5979
Max Act: 8.1604. Min Act: -0.1700
Data Index: 417981 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5979. Min Range: -8.5979
Max Act: 7.9729. Min Act: -0.1700
Data Index: 6742927 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5979. Min Range: -8.5979
Max Act: 7.9104. Min Act: -0.1700
Data Index: 7658477 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5979. Min Range: -8.5979
Max Act: 7.9104. Min Act: -0.1700
Data Index: 5122931 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5979. Min Range: -8.5979
Max Act: 7.8479. Min Act: -0.1700
Data Index: 1191395 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5979. Min Range: -8.5979
Max Act: 7.7229. Min Act: -0.1700
Data Index: 2290085 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5979. Min Range: -8.5979
Max Act: 7.7854. Min Act: -0.1700
Data Index: 4655607 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5979. Min Range: -8.5979
Max Act: 7.7854. Min Act: -0.1700
Data Index: 7397275 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5979. Min Range: -8.5979
Max Act: 7.7854. Min Act: -0.1700
Data Index: 5691567 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5979. Min Range: -8.5979
Max Act: 7.7854. Min Act: -0.1700
Data Index: 7776387 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5979. Min Range: -8.5979
Max Act: 7.7229. Min Act: -0.1700
Data Index: 1296149 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19