Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2770 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.5217. Min Range: -9.5217
Max Act: 9.5217. Min Act: -0.1700
Data Index: 6496343 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5217. Min Range: -9.5217
Max Act: 8.8967. Min Act: -0.1700
Data Index: 7022375 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5217. Min Range: -9.5217
Max Act: 8.7092. Min Act: -0.1700
Data Index: 1488810 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5217. Min Range: -9.5217
Max Act: 8.7092. Min Act: -0.1700
Data Index: 5826595 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5217. Min Range: -9.5217
Max Act: 8.6467. Min Act: -0.1700
Data Index: 3883254 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5217. Min Range: -9.5217
Max Act: 8.6467. Min Act: -0.1700
Data Index: 7032660 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5217. Min Range: -9.5217
Max Act: 8.6467. Min Act: -0.1700
Data Index: 1488814 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5217. Min Range: -9.5217
Max Act: 8.5217. Min Act: -0.1700
Data Index: 7140994 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5217. Min Range: -9.5217
Max Act: 8.5842. Min Act: -0.1700
Data Index: 1130399 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5217. Min Range: -9.5217
Max Act: 8.5217. Min Act: -0.1700
Data Index: 1625873 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5217. Min Range: -9.5217
Max Act: 8.4592. Min Act: -0.1700
Data Index: 2954921 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5217. Min Range: -9.5217
Max Act: 8.3967. Min Act: -0.1700
Data Index: 4933932 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5217. Min Range: -9.5217
Max Act: 8.3967. Min Act: -0.1700
Data Index: 3795753 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5217. Min Range: -9.5217
Max Act: 8.3967. Min Act: -0.1700
Data Index: 610498 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5217. Min Range: -9.5217
Max Act: 8.3342. Min Act: -0.1700
Data Index: 7006233 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5217. Min Range: -9.5217
Max Act: 8.3342. Min Act: -0.1700
Data Index: 4740631 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5217. Min Range: -9.5217
Max Act: 8.3342. Min Act: -0.1700
Data Index: 3892263 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5217. Min Range: -9.5217
Max Act: 8.3342. Min Act: -0.1700
Data Index: 5733603 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5217. Min Range: -9.5217
Max Act: 8.3342. Min Act: -0.1700
Data Index: 8300097 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5217. Min Range: -9.5217
Max Act: 8.2717. Min Act: -0.1700
Data Index: 2133475 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19