Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2172 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4123. Min Range: -2.4123
Max Act: 2.4123. Min Act: -0.1700
Data Index: 5854010 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4123. Min Range: -2.4123
Max Act: 2.3469. Min Act: -0.1700
Data Index: 2141084 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4123. Min Range: -2.4123
Max Act: 2.3305. Min Act: -0.1700
Data Index: 8484701 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4123. Min Range: -2.4123
Max Act: 2.3305. Min Act: -0.1700
Data Index: 8530254 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4123. Min Range: -2.4123
Max Act: 2.3305. Min Act: -0.1700
Data Index: 4440772 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4123. Min Range: -2.4123
Max Act: 2.2976. Min Act: -0.1700
Data Index: 3583940 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4123. Min Range: -2.4123
Max Act: 2.2976. Min Act: -0.1700
Data Index: 230491 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4123. Min Range: -2.4123
Max Act: 2.3141. Min Act: -0.1700
Data Index: 3789445 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4123. Min Range: -2.4123
Max Act: 2.2812. Min Act: -0.1700
Data Index: 541631 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4123. Min Range: -2.4123
Max Act: 2.2812. Min Act: -0.1700
Data Index: 4182712 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4123. Min Range: -2.4123
Max Act: 2.2482. Min Act: -0.1700
Data Index: 4841668 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4123. Min Range: -2.4123
Max Act: 2.2482. Min Act: -0.1700
Data Index: 1892844 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4123. Min Range: -2.4123
Max Act: 2.2482. Min Act: -0.1700
Data Index: 3586761 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4123. Min Range: -2.4123
Max Act: 2.2812. Min Act: -0.1700
Data Index: 2280049 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4123. Min Range: -2.4123
Max Act: 2.2647. Min Act: -0.1700
Data Index: 5521708 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4123. Min Range: -2.4123
Max Act: 2.2647. Min Act: -0.1700
Data Index: 1995452 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4123. Min Range: -2.4123
Max Act: 2.2316. Min Act: -0.1700
Data Index: 8013620 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4123. Min Range: -2.4123
Max Act: 2.2316. Min Act: -0.1700
Data Index: 5489950 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4123. Min Range: -2.4123
Max Act: 2.2482. Min Act: -0.1700
Data Index: 6189904 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4123. Min Range: -2.4123
Max Act: 2.2151. Min Act: -0.1700
Data Index: 2227011 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19