Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3064 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2194. Min Range: -6.2194
Max Act: 6.2194. Min Act: -0.1700
Data Index: 8573234 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2194. Min Range: -6.2194
Max Act: 6.1881. Min Act: -0.1700
Data Index: 4277904 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2194. Min Range: -6.2194
Max Act: 6.1881. Min Act: -0.1700
Data Index: 1665237 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2194. Min Range: -6.2194
Max Act: 6.1569. Min Act: -0.1700
Data Index: 6518937 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2194. Min Range: -6.2194
Max Act: 6.0944. Min Act: -0.1700
Data Index: 2947039 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2194. Min Range: -6.2194
Max Act: 6.0944. Min Act: -0.1700
Data Index: 1231775 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2194. Min Range: -6.2194
Max Act: 6.0944. Min Act: -0.1700
Data Index: 7338120 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2194. Min Range: -6.2194
Max Act: 6.0319. Min Act: -0.1700
Data Index: 3583460 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2194. Min Range: -6.2194
Max Act: 6.0006. Min Act: -0.1700
Data Index: 1301876 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2194. Min Range: -6.2194
Max Act: 6.0006. Min Act: -0.1700
Data Index: 3656154 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2194. Min Range: -6.2194
Max Act: 6.0319. Min Act: -0.1700
Data Index: 2821754 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.9694. Min Act: -0.1700
Data Index: 1510894 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.9694. Min Act: -0.1700
Data Index: 1605259 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.9694. Min Act: -0.1700
Data Index: 397452 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.9069. Min Act: -0.1700
Data Index: 3757887 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.9069. Min Act: -0.1700
Data Index: 3461458 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.9069. Min Act: -0.1700
Data Index: 5252930 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.9069. Min Act: -0.1700
Data Index: 3517846 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.8756. Min Act: -0.1700
Data Index: 4179254 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.8756. Min Act: -0.1700
Data Index: 4505313 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19