Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2428 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1787. Min Range: -7.1787
Max Act: 7.1787. Min Act: -0.1700
Data Index: 6906791 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1787. Min Range: -7.1787
Max Act: 7.1475. Min Act: -0.1700
Data Index: 5587971 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1787. Min Range: -7.1787
Max Act: 7.0537. Min Act: -0.1700
Data Index: 1914879 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1787. Min Range: -7.1787
Max Act: 6.9600. Min Act: -0.1700
Data Index: 2761263 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1787. Min Range: -7.1787
Max Act: 6.8350. Min Act: -0.1700
Data Index: 526840 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1787. Min Range: -7.1787
Max Act: 6.8037. Min Act: -0.1700
Data Index: 7637126 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1787. Min Range: -7.1787
Max Act: 6.7100. Min Act: -0.1700
Data Index: 8533821 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1787. Min Range: -7.1787
Max Act: 6.6475. Min Act: -0.1700
Data Index: 6888433 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1787. Min Range: -7.1787
Max Act: 6.6787. Min Act: -0.1700
Data Index: 8108924 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1787. Min Range: -7.1787
Max Act: 6.6162. Min Act: -0.1700
Data Index: 4289031 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1787. Min Range: -7.1787
Max Act: 6.5537. Min Act: -0.1700
Data Index: 1421674 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1787. Min Range: -7.1787
Max Act: 6.5537. Min Act: -0.1700
Data Index: 7867662 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1787. Min Range: -7.1787
Max Act: 6.5537. Min Act: -0.1700
Data Index: 5071111 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1787. Min Range: -7.1787
Max Act: 6.5225. Min Act: -0.1700
Data Index: 6655159 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1787. Min Range: -7.1787
Max Act: 6.5225. Min Act: -0.1700
Data Index: 6857430 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1787. Min Range: -7.1787
Max Act: 6.5225. Min Act: -0.1700
Data Index: 3659946 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1787. Min Range: -7.1787
Max Act: 6.5225. Min Act: -0.1700
Data Index: 6131705 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1787. Min Range: -7.1787
Max Act: 6.5225. Min Act: -0.1700
Data Index: 7630920 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1787. Min Range: -7.1787
Max Act: 6.5225. Min Act: -0.1700
Data Index: 2290083 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1787. Min Range: -7.1787
Max Act: 6.5225. Min Act: -0.1700
Data Index: 6279555 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19