Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3818 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9701. Min Range: -3.9701
Max Act: 3.9701. Min Act: -0.1700
Data Index: 6701844 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9701. Min Range: -3.9701
Max Act: 3.8607. Min Act: -0.1700
Data Index: 1800599 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9701. Min Range: -3.9701
Max Act: 3.7982. Min Act: -0.1700
Data Index: 4082941 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9701. Min Range: -3.9701
Max Act: 3.7982. Min Act: -0.1700
Data Index: 4509935 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9701. Min Range: -3.9701
Max Act: 3.7512. Min Act: -0.1700
Data Index: 2046415 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9701. Min Range: -3.9701
Max Act: 3.7200. Min Act: -0.1700
Data Index: 7337137 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9701. Min Range: -3.9701
Max Act: 3.7356. Min Act: -0.1700
Data Index: 2238474 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9701. Min Range: -3.9701
Max Act: 3.7356. Min Act: -0.1700
Data Index: 5875860 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9701. Min Range: -3.9701
Max Act: 3.7356. Min Act: -0.1700
Data Index: 185820 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9701. Min Range: -3.9701
Max Act: 3.7356. Min Act: -0.1700
Data Index: 1703000 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9701. Min Range: -3.9701
Max Act: 3.7200. Min Act: -0.1700
Data Index: 5875859 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9701. Min Range: -3.9701
Max Act: 3.7043. Min Act: -0.1700
Data Index: 7542541 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9701. Min Range: -3.9701
Max Act: 3.6887. Min Act: -0.1700
Data Index: 8559944 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9701. Min Range: -3.9701
Max Act: 3.6574. Min Act: -0.1700
Data Index: 7147986 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9701. Min Range: -3.9701
Max Act: 3.6730. Min Act: -0.1700
Data Index: 4076907 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9701. Min Range: -3.9701
Max Act: 3.6261. Min Act: -0.1700
Data Index: 8573830 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9701. Min Range: -3.9701
Max Act: 3.6261. Min Act: -0.1700
Data Index: 1107973 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9701. Min Range: -3.9701
Max Act: 3.5948. Min Act: -0.1700
Data Index: 2856029 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9701. Min Range: -3.9701
Max Act: 3.6104. Min Act: -0.1700
Data Index: 1047230 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9701. Min Range: -3.9701
Max Act: 3.5948. Min Act: -0.1700
Data Index: 8465066 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19