Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3576 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3942. Min Range: -6.3942
Max Act: 6.3942. Min Act: -0.1700
Data Index: 7584549 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3942. Min Range: -6.3942
Max Act: 6.3004. Min Act: -0.1700
Data Index: 2806250 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3942. Min Range: -6.3942
Max Act: 5.9254. Min Act: -0.1700
Data Index: 6714387 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3942. Min Range: -6.3942
Max Act: 5.8629. Min Act: -0.1700
Data Index: 1005967 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3942. Min Range: -6.3942
Max Act: 5.8629. Min Act: -0.1700
Data Index: 8297720 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3942. Min Range: -6.3942
Max Act: 5.8629. Min Act: -0.1700
Data Index: 3257652 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3942. Min Range: -6.3942
Max Act: 5.8629. Min Act: -0.1700
Data Index: 601214 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3942. Min Range: -6.3942
Max Act: 5.8317. Min Act: -0.1700
Data Index: 782262 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3942. Min Range: -6.3942
Max Act: 5.7692. Min Act: -0.1700
Data Index: 2209770 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3942. Min Range: -6.3942
Max Act: 5.7692. Min Act: -0.1700
Data Index: 4286368 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3942. Min Range: -6.3942
Max Act: 5.7379. Min Act: -0.1700
Data Index: 810129 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3942. Min Range: -6.3942
Max Act: 5.7067. Min Act: -0.1700
Data Index: 6178450 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3942. Min Range: -6.3942
Max Act: 5.7067. Min Act: -0.1700
Data Index: 6419057 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3942. Min Range: -6.3942
Max Act: 5.6129. Min Act: -0.1700
Data Index: 3342346 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3942. Min Range: -6.3942
Max Act: 5.5817. Min Act: -0.1700
Data Index: 6787897 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3942. Min Range: -6.3942
Max Act: 5.5192. Min Act: -0.1700
Data Index: 8115634 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3942. Min Range: -6.3942
Max Act: 5.5817. Min Act: -0.1700
Data Index: 6277200 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3942. Min Range: -6.3942
Max Act: 5.5504. Min Act: -0.1700
Data Index: 4935508 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3942. Min Range: -6.3942
Max Act: 5.5192. Min Act: -0.1700
Data Index: 5739499 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3942. Min Range: -6.3942
Max Act: 5.5192. Min Act: -0.1700
Data Index: 4756026 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19