Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3169 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6862. Min Range: -3.6862
Max Act: 3.6862. Min Act: -0.1700
Data Index: 1535662 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6862. Min Range: -3.6862
Max Act: 3.6549. Min Act: -0.1700
Data Index: 4942050 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6862. Min Range: -3.6862
Max Act: 3.6862. Min Act: -0.1700
Data Index: 4833512 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6862. Min Range: -3.6862
Max Act: 3.6393. Min Act: -0.1700
Data Index: 6396618 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6862. Min Range: -3.6862
Max Act: 3.6080. Min Act: -0.1700
Data Index: 7285743 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6862. Min Range: -3.6862
Max Act: 3.6080. Min Act: -0.1700
Data Index: 1608038 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6862. Min Range: -3.6862
Max Act: 3.5923. Min Act: -0.1700
Data Index: 5438654 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6862. Min Range: -3.6862
Max Act: 3.5767. Min Act: -0.1700
Data Index: 6971720 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6862. Min Range: -3.6862
Max Act: 3.5767. Min Act: -0.1700
Data Index: 8287769 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6862. Min Range: -3.6862
Max Act: 3.5454. Min Act: -0.1700
Data Index: 4749671 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6862. Min Range: -3.6862
Max Act: 3.5454. Min Act: -0.1700
Data Index: 1046296 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6862. Min Range: -3.6862
Max Act: 3.5297. Min Act: -0.1700
Data Index: 2517162 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6862. Min Range: -3.6862
Max Act: 3.5767. Min Act: -0.1700
Data Index: 3188047 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6862. Min Range: -3.6862
Max Act: 3.4514. Min Act: -0.1700
Data Index: 3047648 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6862. Min Range: -3.6862
Max Act: 3.5454. Min Act: -0.1700
Data Index: 1158868 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6862. Min Range: -3.6862
Max Act: 3.5297. Min Act: -0.1700
Data Index: 7957991 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6862. Min Range: -3.6862
Max Act: 3.5297. Min Act: -0.1700
Data Index: 4465013 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6862. Min Range: -3.6862
Max Act: 3.4200. Min Act: -0.1700
Data Index: 5634071 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6862. Min Range: -3.6862
Max Act: 3.5297. Min Act: -0.1700
Data Index: 2229989 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6862. Min Range: -3.6862
Max Act: 3.4357. Min Act: -0.1700
Data Index: 194179 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19