Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2263 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9585. Min Range: -7.9585
Max Act: 7.9585. Min Act: -0.1700
Data Index: 3679206 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9585. Min Range: -7.9585
Max Act: 7.9585. Min Act: -0.1700
Data Index: 6222192 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9585. Min Range: -7.9585
Max Act: 7.8648. Min Act: -0.1700
Data Index: 64311 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9585. Min Range: -7.9585
Max Act: 7.8960. Min Act: -0.1700
Data Index: 4591631 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9585. Min Range: -7.9585
Max Act: 7.8960. Min Act: -0.1700
Data Index: 8245722 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9585. Min Range: -7.9585
Max Act: 7.7085. Min Act: -0.1700
Data Index: 7507794 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9585. Min Range: -7.9585
Max Act: 7.7398. Min Act: -0.1700
Data Index: 2839172 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9585. Min Range: -7.9585
Max Act: 7.6460. Min Act: -0.1700
Data Index: 8179221 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9585. Min Range: -7.9585
Max Act: 7.5210. Min Act: -0.1700
Data Index: 6436084 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9585. Min Range: -7.9585
Max Act: 7.5210. Min Act: -0.1700
Data Index: 8301737 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9585. Min Range: -7.9585
Max Act: 7.5210. Min Act: -0.1700
Data Index: 4402422 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9585. Min Range: -7.9585
Max Act: 7.5210. Min Act: -0.1700
Data Index: 4708225 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9585. Min Range: -7.9585
Max Act: 7.4898. Min Act: -0.1700
Data Index: 5971479 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9585. Min Range: -7.9585
Max Act: 7.4898. Min Act: -0.1700
Data Index: 2062805 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9585. Min Range: -7.9585
Max Act: 7.4585. Min Act: -0.1700
Data Index: 4518054 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9585. Min Range: -7.9585
Max Act: 7.4585. Min Act: -0.1700
Data Index: 537540 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9585. Min Range: -7.9585
Max Act: 7.4273. Min Act: -0.1700
Data Index: 7729149 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9585. Min Range: -7.9585
Max Act: 7.3960. Min Act: -0.1700
Data Index: 551727 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9585. Min Range: -7.9585
Max Act: 7.3648. Min Act: -0.1700
Data Index: 319371 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9585. Min Range: -7.9585
Max Act: 7.3648. Min Act: -0.1700
Data Index: 2326590 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19