Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 842 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6585. Min Range: -3.6585
Max Act: 3.6585. Min Act: -0.1700
Data Index: 6664330 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6585. Min Range: -3.6585
Max Act: 3.5646. Min Act: -0.1700
Data Index: 3620983 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6585. Min Range: -3.6585
Max Act: 3.6272. Min Act: -0.1700
Data Index: 8501373 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6585. Min Range: -3.6585
Max Act: 3.5019. Min Act: -0.1700
Data Index: 8319059 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6585. Min Range: -3.6585
Max Act: 3.4706. Min Act: -0.1700
Data Index: 4649763 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6585. Min Range: -3.6585
Max Act: 3.4863. Min Act: -0.1700
Data Index: 8630203 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6585. Min Range: -3.6585
Max Act: 3.4706. Min Act: -0.1700
Data Index: 2177683 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6585. Min Range: -3.6585
Max Act: 3.4549. Min Act: -0.1700
Data Index: 8591053 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6585. Min Range: -3.6585
Max Act: 3.4393. Min Act: -0.1700
Data Index: 8252896 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6585. Min Range: -3.6585
Max Act: 3.3609. Min Act: -0.1700
Data Index: 7721296 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6585. Min Range: -3.6585
Max Act: 3.3765. Min Act: -0.1700
Data Index: 3827141 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6585. Min Range: -3.6585
Max Act: 3.3609. Min Act: -0.1700
Data Index: 6942962 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6585. Min Range: -3.6585
Max Act: 3.3452. Min Act: -0.1700
Data Index: 5536302 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6585. Min Range: -3.6585
Max Act: 3.3138. Min Act: -0.1700
Data Index: 1116423 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6585. Min Range: -3.6585
Max Act: 3.2981. Min Act: -0.1700
Data Index: 4097200 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6585. Min Range: -3.6585
Max Act: 3.3295. Min Act: -0.1700
Data Index: 7432795 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6585. Min Range: -3.6585
Max Act: 3.3138. Min Act: -0.1700
Data Index: 7383209 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6585. Min Range: -3.6585
Max Act: 3.3138. Min Act: -0.1700
Data Index: 281685 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6585. Min Range: -3.6585
Max Act: 3.3138. Min Act: -0.1700
Data Index: 1073856 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6585. Min Range: -3.6585
Max Act: 3.3138. Min Act: -0.1700
Data Index: 1494808 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19