Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 323 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.3982. Min Act: -0.1700
Data Index: 6334335 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.3357. Min Act: -0.1700
Data Index: 6791550 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.3357. Min Act: -0.1700
Data Index: 7553947 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.3357. Min Act: -0.1700
Data Index: 6310749 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.3357. Min Act: -0.1700
Data Index: 4842780 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.3044. Min Act: -0.1700
Data Index: 2588280 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.2107. Min Act: -0.1700
Data Index: 4130911 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.2419. Min Act: -0.1700
Data Index: 884199 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.1794. Min Act: -0.1700
Data Index: 2036736 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.1794. Min Act: -0.1700
Data Index: 4920157 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.1794. Min Act: -0.1700
Data Index: 958744 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.2107. Min Act: -0.1700
Data Index: 697820 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.1482. Min Act: -0.1700
Data Index: 6916151 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.0857. Min Act: -0.1700
Data Index: 3712487 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.0544. Min Act: -0.1700
Data Index: 1253934 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.0232. Min Act: -0.1700
Data Index: 6768969 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3982. Min Range: -6.3982
Max Act: 6.0232. Min Act: -0.1700
Data Index: 3581216 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3982. Min Range: -6.3982
Max Act: 5.9919. Min Act: -0.1700
Data Index: 1997795 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3982. Min Range: -6.3982
Max Act: 5.9294. Min Act: -0.1700
Data Index: 5175530 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3982. Min Range: -6.3982
Max Act: 5.9607. Min Act: -0.1700
Data Index: 6675330 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19