Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3054 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6569. Min Range: -7.6569
Max Act: 7.6569. Min Act: -0.1700
Data Index: 8596886 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6569. Min Range: -7.6569
Max Act: 7.5319. Min Act: -0.1700
Data Index: 5041013 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6569. Min Range: -7.6569
Max Act: 7.4069. Min Act: -0.1700
Data Index: 1356542 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6569. Min Range: -7.6569
Max Act: 7.2507. Min Act: -0.1700
Data Index: 738265 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6569. Min Range: -7.6569
Max Act: 7.2507. Min Act: -0.1700
Data Index: 122009 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6569. Min Range: -7.6569
Max Act: 7.2194. Min Act: -0.1700
Data Index: 1824434 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6569. Min Range: -7.6569
Max Act: 7.2194. Min Act: -0.1700
Data Index: 4811471 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6569. Min Range: -7.6569
Max Act: 7.2194. Min Act: -0.1700
Data Index: 2395386 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6569. Min Range: -7.6569
Max Act: 7.2194. Min Act: -0.1700
Data Index: 7033574 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6569. Min Range: -7.6569
Max Act: 7.1882. Min Act: -0.1700
Data Index: 3427744 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6569. Min Range: -7.6569
Max Act: 7.0944. Min Act: -0.1700
Data Index: 279531 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6569. Min Range: -7.6569
Max Act: 7.1569. Min Act: -0.1700
Data Index: 2844163 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6569. Min Range: -7.6569
Max Act: 7.1257. Min Act: -0.1700
Data Index: 889326 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6569. Min Range: -7.6569
Max Act: 7.1569. Min Act: -0.1700
Data Index: 5262340 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6569. Min Range: -7.6569
Max Act: 7.1257. Min Act: -0.1700
Data Index: 7335574 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6569. Min Range: -7.6569
Max Act: 7.1257. Min Act: -0.1700
Data Index: 848655 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6569. Min Range: -7.6569
Max Act: 7.1569. Min Act: -0.1700
Data Index: 8322458 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6569. Min Range: -7.6569
Max Act: 7.1257. Min Act: -0.1700
Data Index: 5041014 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6569. Min Range: -7.6569
Max Act: 7.0944. Min Act: -0.1700
Data Index: 810188 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6569. Min Range: -7.6569
Max Act: 7.0944. Min Act: -0.1700
Data Index: 8168902 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19