Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 978 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3422. Min Range: -5.3422
Max Act: 5.3422. Min Act: -0.1700
Data Index: 3764973 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3422. Min Range: -5.3422
Max Act: 5.3110. Min Act: -0.1700
Data Index: 442627 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3422. Min Range: -5.3422
Max Act: 5.2172. Min Act: -0.1700
Data Index: 2880421 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3422. Min Range: -5.3422
Max Act: 5.1235. Min Act: -0.1700
Data Index: 3589843 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3422. Min Range: -5.3422
Max Act: 5.0610. Min Act: -0.1700
Data Index: 2485898 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3422. Min Range: -5.3422
Max Act: 5.0610. Min Act: -0.1700
Data Index: 4263734 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3422. Min Range: -5.3422
Max Act: 5.0610. Min Act: -0.1700
Data Index: 1768718 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3422. Min Range: -5.3422
Max Act: 5.0610. Min Act: -0.1700
Data Index: 956800 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3422. Min Range: -5.3422
Max Act: 5.0297. Min Act: -0.1700
Data Index: 7266351 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3422. Min Range: -5.3422
Max Act: 5.0297. Min Act: -0.1700
Data Index: 1903876 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3422. Min Range: -5.3422
Max Act: 5.0297. Min Act: -0.1700
Data Index: 4170758 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3422. Min Range: -5.3422
Max Act: 4.9672. Min Act: -0.1700
Data Index: 5429754 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3422. Min Range: -5.3422
Max Act: 4.9672. Min Act: -0.1700
Data Index: 8170936 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3422. Min Range: -5.3422
Max Act: 4.9360. Min Act: -0.1700
Data Index: 2116911 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3422. Min Range: -5.3422
Max Act: 4.9672. Min Act: -0.1700
Data Index: 3042149 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3422. Min Range: -5.3422
Max Act: 4.9672. Min Act: -0.1700
Data Index: 5651173 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3422. Min Range: -5.3422
Max Act: 4.9360. Min Act: -0.1700
Data Index: 736844 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3422. Min Range: -5.3422
Max Act: 4.9360. Min Act: -0.1700
Data Index: 3520904 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3422. Min Range: -5.3422
Max Act: 4.9360. Min Act: -0.1700
Data Index: 4591227 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3422. Min Range: -5.3422
Max Act: 4.9360. Min Act: -0.1700
Data Index: 7327879 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19