Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2925 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5123. Min Range: -4.5123
Max Act: 4.5123. Min Act: -0.1700
Data Index: 2195399 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5123. Min Range: -4.5123
Max Act: 4.3560. Min Act: -0.1700
Data Index: 1839998 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5123. Min Range: -4.5123
Max Act: 4.3873. Min Act: -0.1700
Data Index: 1793340 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5123. Min Range: -4.5123
Max Act: 4.3560. Min Act: -0.1700
Data Index: 4687525 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5123. Min Range: -4.5123
Max Act: 4.3248. Min Act: -0.1700
Data Index: 8224597 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5123. Min Range: -4.5123
Max Act: 4.3248. Min Act: -0.1700
Data Index: 4302795 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5123. Min Range: -4.5123
Max Act: 4.2623. Min Act: -0.1700
Data Index: 4540212 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5123. Min Range: -4.5123
Max Act: 4.2935. Min Act: -0.1700
Data Index: 6944722 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5123. Min Range: -4.5123
Max Act: 4.2623. Min Act: -0.1700
Data Index: 8622919 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5123. Min Range: -4.5123
Max Act: 4.2935. Min Act: -0.1699
Data Index: 1622385 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5123. Min Range: -4.5123
Max Act: 4.2935. Min Act: -0.1700
Data Index: 5413951 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5123. Min Range: -4.5123
Max Act: 4.2623. Min Act: -0.1700
Data Index: 4649473 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5123. Min Range: -4.5123
Max Act: 4.2935. Min Act: -0.1700
Data Index: 2295560 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5123. Min Range: -4.5123
Max Act: 4.2623. Min Act: -0.1700
Data Index: 4933878 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5123. Min Range: -4.5123
Max Act: 4.2623. Min Act: -0.1700
Data Index: 7186457 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5123. Min Range: -4.5123
Max Act: 4.2623. Min Act: -0.1700
Data Index: 1997998 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5123. Min Range: -4.5123
Max Act: 4.2623. Min Act: -0.1700
Data Index: 5154481 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5123. Min Range: -4.5123
Max Act: 4.2623. Min Act: -0.1700
Data Index: 179248 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5123. Min Range: -4.5123
Max Act: 4.2623. Min Act: -0.1700
Data Index: 3835415 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5123. Min Range: -4.5123
Max Act: 4.2623. Min Act: -0.1700
Data Index: 5637751 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19