Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 796 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8955. Min Range: -2.8955
Max Act: 2.8955. Min Act: -0.1700
Data Index: 7103852 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8955. Min Range: -2.8955
Max Act: 2.8637. Min Act: -0.1700
Data Index: 4606668 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8955. Min Range: -2.8955
Max Act: 2.8319. Min Act: -0.1700
Data Index: 3584339 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8955. Min Range: -2.8955
Max Act: 2.7523. Min Act: -0.1700
Data Index: 8121870 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8955. Min Range: -2.8955
Max Act: 2.7203. Min Act: -0.1700
Data Index: 7293000 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8955. Min Range: -2.8955
Max Act: 2.7044. Min Act: -0.1700
Data Index: 8539281 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8955. Min Range: -2.8955
Max Act: 2.7044. Min Act: -0.1700
Data Index: 7266701 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8955. Min Range: -2.8955
Max Act: 2.6883. Min Act: -0.1700
Data Index: 4678174 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8955. Min Range: -2.8955
Max Act: 2.6563. Min Act: -0.1700
Data Index: 7781696 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8955. Min Range: -2.8955
Max Act: 2.6883. Min Act: -0.1700
Data Index: 5587859 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8955. Min Range: -2.8955
Max Act: 2.6723. Min Act: -0.1700
Data Index: 806022 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8955. Min Range: -2.8955
Max Act: 2.6883. Min Act: -0.1700
Data Index: 6246489 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8955. Min Range: -2.8955
Max Act: 2.6402. Min Act: -0.1700
Data Index: 3436222 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8955. Min Range: -2.8955
Max Act: 2.6402. Min Act: -0.1700
Data Index: 3226397 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8955. Min Range: -2.8955
Max Act: 2.6723. Min Act: -0.1700
Data Index: 7832584 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8955. Min Range: -2.8955
Max Act: 2.6402. Min Act: -0.1700
Data Index: 5577946 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8955. Min Range: -2.8955
Max Act: 2.6402. Min Act: -0.1700
Data Index: 3507168 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8955. Min Range: -2.8955
Max Act: 2.6402. Min Act: -0.1700
Data Index: 4408752 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8955. Min Range: -2.8955
Max Act: 2.6402. Min Act: -0.1700
Data Index: 8215290 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8955. Min Range: -2.8955
Max Act: 2.6402. Min Act: -0.1700
Data Index: 5994906 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19