Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2801 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1298. Min Range: -5.1298
Max Act: 5.1298. Min Act: -0.1700
Data Index: 5893222 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1298. Min Range: -5.1298
Max Act: 5.1298. Min Act: -0.1700
Data Index: 5759486 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1298. Min Range: -5.1298
Max Act: 5.0986. Min Act: -0.1700
Data Index: 4157486 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1298. Min Range: -5.1298
Max Act: 4.9423. Min Act: -0.1700
Data Index: 7843765 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1298. Min Range: -5.1298
Max Act: 4.9111. Min Act: -0.1700
Data Index: 1774994 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1298. Min Range: -5.1298
Max Act: 4.9111. Min Act: -0.1700
Data Index: 7212734 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1298. Min Range: -5.1298
Max Act: 4.8798. Min Act: -0.1700
Data Index: 6518075 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1298. Min Range: -5.1298
Max Act: 4.8486. Min Act: -0.1700
Data Index: 5223435 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1298. Min Range: -5.1298
Max Act: 4.8486. Min Act: -0.1700
Data Index: 742336 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1298. Min Range: -5.1298
Max Act: 4.8173. Min Act: -0.1700
Data Index: 3036567 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1298. Min Range: -5.1298
Max Act: 4.8173. Min Act: -0.1700
Data Index: 334893 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1298. Min Range: -5.1298
Max Act: 4.7861. Min Act: -0.1700
Data Index: 4290797 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1298. Min Range: -5.1298
Max Act: 4.7861. Min Act: -0.1700
Data Index: 7938796 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1298. Min Range: -5.1298
Max Act: 4.7548. Min Act: -0.1700
Data Index: 7664600 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1298. Min Range: -5.1298
Max Act: 4.7861. Min Act: -0.1700
Data Index: 6683772 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1298. Min Range: -5.1298
Max Act: 4.7548. Min Act: -0.1700
Data Index: 6958061 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1298. Min Range: -5.1298
Max Act: 4.7548. Min Act: -0.1700
Data Index: 2286566 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1298. Min Range: -5.1298
Max Act: 4.7548. Min Act: -0.1700
Data Index: 4635623 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1298. Min Range: -5.1298
Max Act: 4.7548. Min Act: -0.1700
Data Index: 4617487 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1298. Min Range: -5.1298
Max Act: 4.7548. Min Act: -0.1700
Data Index: 1703307 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19