Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3810 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.9031. Min Range: -7.9031
Max Act: 7.9031. Min Act: -0.1700
Data Index: 8811633 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9031. Min Range: -7.9031
Max Act: 7.8406. Min Act: -0.1700
Data Index: 1059721 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9031. Min Range: -7.9031
Max Act: 7.7156. Min Act: -0.1700
Data Index: 7892768 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9031. Min Range: -7.9031
Max Act: 7.6844. Min Act: -0.1700
Data Index: 6675673 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9031. Min Range: -7.9031
Max Act: 7.6844. Min Act: -0.1700
Data Index: 259903 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9031. Min Range: -7.9031
Max Act: 7.5594. Min Act: -0.1700
Data Index: 7581367 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9031. Min Range: -7.9031
Max Act: 7.6531. Min Act: -0.1700
Data Index: 7546995 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9031. Min Range: -7.9031
Max Act: 7.6531. Min Act: -0.1700
Data Index: 386191 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9031. Min Range: -7.9031
Max Act: 7.5906. Min Act: -0.1700
Data Index: 815075 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9031. Min Range: -7.9031
Max Act: 7.5281. Min Act: -0.1700
Data Index: 5963949 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9031. Min Range: -7.9031
Max Act: 7.5281. Min Act: -0.1700
Data Index: 7361348 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9031. Min Range: -7.9031
Max Act: 7.5906. Min Act: -0.1700
Data Index: 7159945 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9031. Min Range: -7.9031
Max Act: 7.5281. Min Act: -0.1700
Data Index: 6675685 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9031. Min Range: -7.9031
Max Act: 7.4656. Min Act: -0.1700
Data Index: 3019835 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9031. Min Range: -7.9031
Max Act: 7.4656. Min Act: -0.1700
Data Index: 4321491 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9031. Min Range: -7.9031
Max Act: 7.4656. Min Act: -0.1700
Data Index: 7800537 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9031. Min Range: -7.9031
Max Act: 7.5281. Min Act: -0.1700
Data Index: 160660 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9031. Min Range: -7.9031
Max Act: 7.4969. Min Act: -0.1700
Data Index: 5605301 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9031. Min Range: -7.9031
Max Act: 7.4656. Min Act: -0.1700
Data Index: 2087855 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9031. Min Range: -7.9031
Max Act: 7.4969. Min Act: -0.1700
Data Index: 4745666 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19