Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3057 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.5117. Min Range: -14.5117
Max Act: 14.5117. Min Act: -0.1700
Data Index: 4888004 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.5117. Min Range: -14.5117
Max Act: 14.3242. Min Act: -0.1700
Data Index: 699863 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.5117. Min Range: -14.5117
Max Act: 13.5117. Min Act: -0.1700
Data Index: 3342358 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.5117. Min Range: -14.5117
Max Act: 13.3242. Min Act: -0.1700
Data Index: 8134349 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.5117. Min Range: -14.5117
Max Act: 13.1992. Min Act: -0.1700
Data Index: 226711 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.5117. Min Range: -14.5117
Max Act: 13.1367. Min Act: -0.1700
Data Index: 8701083 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.5117. Min Range: -14.5117
Max Act: 13.1367. Min Act: -0.1700
Data Index: 7118553 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.5117. Min Range: -14.5117
Max Act: 13.1367. Min Act: -0.1700
Data Index: 446841 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.5117. Min Range: -14.5117
Max Act: 13.1367. Min Act: -0.1700
Data Index: 6346812 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.5117. Min Range: -14.5117
Max Act: 13.0742. Min Act: -0.1700
Data Index: 2188710 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.5117. Min Range: -14.5117
Max Act: 13.0742. Min Act: -0.1700
Data Index: 1174377 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.5117. Min Range: -14.5117
Max Act: 13.0742. Min Act: -0.1700
Data Index: 2577144 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.5117. Min Range: -14.5117
Max Act: 13.0117. Min Act: -0.1700
Data Index: 4462884 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.5117. Min Range: -14.5117
Max Act: 13.0117. Min Act: -0.1700
Data Index: 7112198 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.5117. Min Range: -14.5117
Max Act: 12.8242. Min Act: -0.1700
Data Index: 3556974 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.5117. Min Range: -14.5117
Max Act: 12.8867. Min Act: -0.1700
Data Index: 5197212 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.5117. Min Range: -14.5117
Max Act: 12.8867. Min Act: -0.1700
Data Index: 2502964 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.5117. Min Range: -14.5117
Max Act: 12.8867. Min Act: -0.1700
Data Index: 1170246 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.5117. Min Range: -14.5117
Max Act: 12.8242. Min Act: -0.1700
Data Index: 6949516 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.5117. Min Range: -14.5117
Max Act: 12.8242. Min Act: -0.1700
Data Index: 7283182 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19