Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 353 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5209. Min Range: -3.5209
Max Act: 3.5209. Min Act: -0.1700
Data Index: 5441199 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5209. Min Range: -3.5209
Max Act: 3.4739. Min Act: -0.1700
Data Index: 7605801 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5209. Min Range: -3.5209
Max Act: 3.4739. Min Act: -0.1700
Data Index: 8403511 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5209. Min Range: -3.5209
Max Act: 3.4739. Min Act: -0.1700
Data Index: 6370963 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5209. Min Range: -3.5209
Max Act: 3.4269. Min Act: -0.1700
Data Index: 8010261 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5209. Min Range: -3.5209
Max Act: 3.4269. Min Act: -0.1700
Data Index: 5573031 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5209. Min Range: -3.5209
Max Act: 3.4112. Min Act: -0.1700
Data Index: 8819824 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5209. Min Range: -3.5209
Max Act: 3.4269. Min Act: -0.1700
Data Index: 4794141 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5209. Min Range: -3.5209
Max Act: 3.4269. Min Act: -0.1700
Data Index: 5985508 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5209. Min Range: -3.5209
Max Act: 3.3955. Min Act: -0.1700
Data Index: 5865068 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5209. Min Range: -3.5209
Max Act: 3.4112. Min Act: -0.1700
Data Index: 5207730 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5209. Min Range: -3.5209
Max Act: 3.4112. Min Act: -0.1700
Data Index: 8179779 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5209. Min Range: -3.5209
Max Act: 3.3798. Min Act: -0.1700
Data Index: 5482352 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5209. Min Range: -3.5209
Max Act: 3.3641. Min Act: -0.1700
Data Index: 2661920 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5209. Min Range: -3.5209
Max Act: 3.3955. Min Act: -0.1700
Data Index: 3656954 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5209. Min Range: -3.5209
Max Act: 3.3798. Min Act: -0.1700
Data Index: 5682068 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5209. Min Range: -3.5209
Max Act: 3.3798. Min Act: -0.1700
Data Index: 7906965 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5209. Min Range: -3.5209
Max Act: 3.3641. Min Act: -0.1700
Data Index: 1268950 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5209. Min Range: -3.5209
Max Act: 3.3641. Min Act: -0.1700
Data Index: 7300172 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5209. Min Range: -3.5209
Max Act: 3.3485. Min Act: -0.1700
Data Index: 7361145 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19