Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2658 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7197. Min Range: -4.7197
Max Act: 4.6884. Min Act: -0.1700
Data Index: 4664414 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7197. Min Range: -4.7197
Max Act: 4.7197. Min Act: -0.1700
Data Index: 2226968 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7197. Min Range: -4.7197
Max Act: 4.6572. Min Act: -0.1700
Data Index: 583499 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7197. Min Range: -4.7197
Max Act: 4.5634. Min Act: -0.1700
Data Index: 8656863 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7197. Min Range: -4.7197
Max Act: 4.5322. Min Act: -0.1700
Data Index: 4770739 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7197. Min Range: -4.7197
Max Act: 4.4697. Min Act: -0.1700
Data Index: 7074439 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7197. Min Range: -4.7197
Max Act: 4.4697. Min Act: -0.1700
Data Index: 6058942 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7197. Min Range: -4.7197
Max Act: 4.5009. Min Act: -0.1700
Data Index: 1018446 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7197. Min Range: -4.7197
Max Act: 4.5009. Min Act: -0.1700
Data Index: 8645662 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7197. Min Range: -4.7197
Max Act: 4.4697. Min Act: -0.1700
Data Index: 2353631 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7197. Min Range: -4.7197
Max Act: 4.4697. Min Act: -0.1700
Data Index: 6490316 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7197. Min Range: -4.7197
Max Act: 4.5009. Min Act: -0.1700
Data Index: 1695099 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7197. Min Range: -4.7197
Max Act: 4.4072. Min Act: -0.1700
Data Index: 4327867 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7197. Min Range: -4.7197
Max Act: 4.4384. Min Act: -0.1700
Data Index: 7287363 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7197. Min Range: -4.7197
Max Act: 4.4072. Min Act: -0.1700
Data Index: 7172026 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7197. Min Range: -4.7197
Max Act: 4.4384. Min Act: -0.1700
Data Index: 4753796 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7197. Min Range: -4.7197
Max Act: 4.3759. Min Act: -0.1700
Data Index: 6060215 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7197. Min Range: -4.7197
Max Act: 4.4072. Min Act: -0.1700
Data Index: 70052 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7197. Min Range: -4.7197
Max Act: 4.4072. Min Act: -0.1700
Data Index: 4632780 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7197. Min Range: -4.7197
Max Act: 4.4072. Min Act: -0.1700
Data Index: 6567265 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19