Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5843 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4935. Min Range: -10.4935
Max Act: 10.4935. Min Act: -0.1700
Data Index: 386319 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4935. Min Range: -10.4935
Max Act: 10.4310. Min Act: -0.1700
Data Index: 386313 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4935. Min Range: -10.4935
Max Act: 10.4310. Min Act: -0.1700
Data Index: 386312 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4935. Min Range: -10.4935
Max Act: 10.4935. Min Act: -0.1700
Data Index: 386314 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4935. Min Range: -10.4935
Max Act: 10.2435. Min Act: -0.1700
Data Index: 386316 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4935. Min Range: -10.4935
Max Act: 10.0560. Min Act: -0.1700
Data Index: 386318 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4935. Min Range: -10.4935
Max Act: 9.9935. Min Act: -0.1700
Data Index: 386315 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4935. Min Range: -10.4935
Max Act: 9.6810. Min Act: -0.1700
Data Index: 1363850 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4935. Min Range: -10.4935
Max Act: 9.6185. Min Act: -0.1700
Data Index: 386320 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4935. Min Range: -10.4935
Max Act: 9.5560. Min Act: -0.1700
Data Index: 8505542 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4935. Min Range: -10.4935
Max Act: 9.6185. Min Act: -0.1700
Data Index: 5811723 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4935. Min Range: -10.4935
Max Act: 9.5560. Min Act: -0.1700
Data Index: 6666256 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4935. Min Range: -10.4935
Max Act: 9.4310. Min Act: -0.1700
Data Index: 5193836 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4935. Min Range: -10.4935
Max Act: 9.2435. Min Act: -0.1700
Data Index: 4013425 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4935. Min Range: -10.4935
Max Act: 9.3060. Min Act: -0.1700
Data Index: 8034548 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4935. Min Range: -10.4935
Max Act: 9.3060. Min Act: -0.1700
Data Index: 5750805 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4935. Min Range: -10.4935
Max Act: 9.3060. Min Act: -0.1700
Data Index: 2131297 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4935. Min Range: -10.4935
Max Act: 9.3060. Min Act: -0.1700
Data Index: 5118322 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4935. Min Range: -10.4935
Max Act: 9.1810. Min Act: -0.1700
Data Index: 2132693 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4935. Min Range: -10.4935
Max Act: 9.1810. Min Act: -0.1700
Data Index: 6213466 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19