Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2649 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4358. Min Range: -6.4358
Max Act: 6.4358. Min Act: -0.1700
Data Index: 6857756 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4358. Min Range: -6.4358
Max Act: 6.2795. Min Act: -0.1700
Data Index: 2315341 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4358. Min Range: -6.4358
Max Act: 6.3420. Min Act: -0.1700
Data Index: 8751803 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4358. Min Range: -6.4358
Max Act: 6.1858. Min Act: -0.1700
Data Index: 7730702 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4358. Min Range: -6.4358
Max Act: 6.0920. Min Act: -0.1700
Data Index: 2215924 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4358. Min Range: -6.4358
Max Act: 6.0608. Min Act: -0.1700
Data Index: 3005405 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4358. Min Range: -6.4358
Max Act: 6.0920. Min Act: -0.1700
Data Index: 5569533 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4358. Min Range: -6.4358
Max Act: 6.0608. Min Act: -0.1700
Data Index: 8400864 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4358. Min Range: -6.4358
Max Act: 5.9670. Min Act: -0.1700
Data Index: 3746969 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4358. Min Range: -6.4358
Max Act: 5.8733. Min Act: -0.1700
Data Index: 1968821 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4358. Min Range: -6.4358
Max Act: 5.9358. Min Act: -0.1700
Data Index: 2541575 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4358. Min Range: -6.4358
Max Act: 5.8108. Min Act: -0.1700
Data Index: 4557417 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4358. Min Range: -6.4358
Max Act: 5.8108. Min Act: -0.1700
Data Index: 4748836 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4358. Min Range: -6.4358
Max Act: 5.7483. Min Act: -0.1700
Data Index: 6904943 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4358. Min Range: -6.4358
Max Act: 5.8420. Min Act: -0.1700
Data Index: 8794400 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4358. Min Range: -6.4358
Max Act: 5.7795. Min Act: -0.1700
Data Index: 1798907 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4358. Min Range: -6.4358
Max Act: 5.8108. Min Act: -0.1700
Data Index: 2891358 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4358. Min Range: -6.4358
Max Act: 5.7170. Min Act: -0.1700
Data Index: 7997756 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4358. Min Range: -6.4358
Max Act: 5.7170. Min Act: -0.1700
Data Index: 1321973 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4358. Min Range: -6.4358
Max Act: 5.7483. Min Act: -0.1700
Data Index: 6609677 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19