Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 10 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.5853. Min Act: -0.1700
Data Index: 3060362 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.4290. Min Act: -0.1700
Data Index: 3670415 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.3978. Min Act: -0.1700
Data Index: 1419491 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.3665. Min Act: -0.1700
Data Index: 6109911 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.3665. Min Act: -0.1700
Data Index: 3907376 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.3353. Min Act: -0.1700
Data Index: 8634460 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.3353. Min Act: -0.1700
Data Index: 6316154 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.3040. Min Act: -0.1700
Data Index: 1432420 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.2728. Min Act: -0.1700
Data Index: 8209763 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.2728. Min Act: -0.1700
Data Index: 5458525 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.3040. Min Act: -0.1700
Data Index: 6739672 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.2728. Min Act: -0.1700
Data Index: 6383261 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.3353. Min Act: -0.1700
Data Index: 4075750 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.3040. Min Act: -0.1700
Data Index: 1087673 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.3353. Min Act: -0.1700
Data Index: 963637 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.2728. Min Act: -0.1700
Data Index: 1823783 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.2415. Min Act: -0.1700
Data Index: 6617794 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.2415. Min Act: -0.1700
Data Index: 5180925 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.2728. Min Act: -0.1700
Data Index: 7398510 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5853. Min Range: -4.5853
Max Act: 4.2728. Min Act: -0.1700
Data Index: 6080069 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19