Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4902 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9897. Min Range: -3.9897
Max Act: 3.9897. Min Act: -0.1700
Data Index: 2725953 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9897. Min Range: -3.9897
Max Act: 3.8959. Min Act: -0.1700
Data Index: 886475 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9897. Min Range: -3.9897
Max Act: 3.8646. Min Act: -0.1700
Data Index: 4174125 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9897. Min Range: -3.9897
Max Act: 3.8334. Min Act: -0.1700
Data Index: 6187061 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9897. Min Range: -3.9897
Max Act: 3.8334. Min Act: -0.1700
Data Index: 8543283 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9897. Min Range: -3.9897
Max Act: 3.7865. Min Act: -0.1700
Data Index: 2045663 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9897. Min Range: -3.9897
Max Act: 3.6770. Min Act: -0.1700
Data Index: 6187060 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9897. Min Range: -3.9897
Max Act: 3.6300. Min Act: -0.1700
Data Index: 5878416 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9897. Min Range: -3.9897
Max Act: 3.5987. Min Act: -0.1700
Data Index: 1250527 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9897. Min Range: -3.9897
Max Act: 3.5518. Min Act: -0.1700
Data Index: 7524601 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9897. Min Range: -3.9897
Max Act: 3.5518. Min Act: -0.1700
Data Index: 3311376 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9897. Min Range: -3.9897
Max Act: 3.5518. Min Act: -0.1700
Data Index: 6552695 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9897. Min Range: -3.9897
Max Act: 3.5204. Min Act: -0.1700
Data Index: 46415 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9897. Min Range: -3.9897
Max Act: 3.5361. Min Act: -0.1700
Data Index: 410889 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9897. Min Range: -3.9897
Max Act: 3.4891. Min Act: -0.1700
Data Index: 8577958 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9897. Min Range: -3.9897
Max Act: 3.5361. Min Act: -0.1700
Data Index: 25186 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9897. Min Range: -3.9897
Max Act: 3.5048. Min Act: -0.1700
Data Index: 996653 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9897. Min Range: -3.9897
Max Act: 3.5048. Min Act: -0.1700
Data Index: 3329431 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9897. Min Range: -3.9897
Max Act: 3.4891. Min Act: -0.1700
Data Index: 8043184 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9897. Min Range: -3.9897
Max Act: 3.4421. Min Act: -0.1700
Data Index: 8553480 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19