Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 633 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4534. Min Range: -6.4534
Max Act: 6.4534. Min Act: -0.1700
Data Index: 3978861 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4534. Min Range: -6.4534
Max Act: 6.4534. Min Act: -0.1700
Data Index: 7244357 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4534. Min Range: -6.4534
Max Act: 6.3909. Min Act: -0.1700
Data Index: 843591 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4534. Min Range: -6.4534
Max Act: 6.3597. Min Act: -0.1700
Data Index: 5362649 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4534. Min Range: -6.4534
Max Act: 6.3597. Min Act: -0.1700
Data Index: 2652019 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4534. Min Range: -6.4534
Max Act: 6.3284. Min Act: -0.1700
Data Index: 7167562 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4534. Min Range: -6.4534
Max Act: 6.2659. Min Act: -0.1700
Data Index: 2646998 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4534. Min Range: -6.4534
Max Act: 6.2659. Min Act: -0.1700
Data Index: 6350859 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4534. Min Range: -6.4534
Max Act: 6.2659. Min Act: -0.1700
Data Index: 3986843 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4534. Min Range: -6.4534
Max Act: 6.2034. Min Act: -0.1700
Data Index: 8527848 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4534. Min Range: -6.4534
Max Act: 6.2347. Min Act: -0.1700
Data Index: 5951030 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4534. Min Range: -6.4534
Max Act: 6.2034. Min Act: -0.1700
Data Index: 1995075 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4534. Min Range: -6.4534
Max Act: 6.2347. Min Act: -0.1700
Data Index: 6504823 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4534. Min Range: -6.4534
Max Act: 6.2659. Min Act: -0.1700
Data Index: 1069521 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4534. Min Range: -6.4534
Max Act: 6.2347. Min Act: -0.1700
Data Index: 882239 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4534. Min Range: -6.4534
Max Act: 6.2347. Min Act: -0.1700
Data Index: 4708451 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4534. Min Range: -6.4534
Max Act: 6.2034. Min Act: -0.1700
Data Index: 1907574 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4534. Min Range: -6.4534
Max Act: 6.2034. Min Act: -0.1700
Data Index: 4628933 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4534. Min Range: -6.4534
Max Act: 6.2034. Min Act: -0.1700
Data Index: 4610494 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4534. Min Range: -6.4534
Max Act: 6.2034. Min Act: -0.1700
Data Index: 3200973 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19