Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3740 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1355. Min Range: -6.1355
Max Act: 6.1355. Min Act: -0.1700
Data Index: 2679720 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1355. Min Range: -6.1355
Max Act: 5.6980. Min Act: -0.1700
Data Index: 6490911 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1355. Min Range: -6.1355
Max Act: 5.6667. Min Act: -0.1700
Data Index: 7209694 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1355. Min Range: -6.1355
Max Act: 5.6667. Min Act: -0.1700
Data Index: 4783059 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1355. Min Range: -6.1355
Max Act: 5.6667. Min Act: -0.1700
Data Index: 7114957 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1355. Min Range: -6.1355
Max Act: 5.6042. Min Act: -0.1700
Data Index: 264421 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1355. Min Range: -6.1355
Max Act: 5.6042. Min Act: -0.1700
Data Index: 4609261 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1355. Min Range: -6.1355
Max Act: 5.6042. Min Act: -0.1700
Data Index: 6502018 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1355. Min Range: -6.1355
Max Act: 5.5417. Min Act: -0.1700
Data Index: 4460527 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1355. Min Range: -6.1355
Max Act: 5.5730. Min Act: -0.1700
Data Index: 4460534 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1355. Min Range: -6.1355
Max Act: 5.5730. Min Act: -0.1700
Data Index: 4460533 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1355. Min Range: -6.1355
Max Act: 5.5730. Min Act: -0.1700
Data Index: 1148053 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1355. Min Range: -6.1355
Max Act: 5.5417. Min Act: -0.1700
Data Index: 7874683 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1355. Min Range: -6.1355
Max Act: 5.5105. Min Act: -0.1700
Data Index: 4161910 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1355. Min Range: -6.1355
Max Act: 5.5105. Min Act: -0.1700
Data Index: 4460532 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1355. Min Range: -6.1355
Max Act: 5.5105. Min Act: -0.1700
Data Index: 1158406 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1355. Min Range: -6.1355
Max Act: 5.4792. Min Act: -0.1700
Data Index: 477640 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1355. Min Range: -6.1355
Max Act: 5.4480. Min Act: -0.1700
Data Index: 4460530 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1355. Min Range: -6.1355
Max Act: 5.3855. Min Act: -0.1700
Data Index: 6301108 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1355. Min Range: -6.1355
Max Act: 5.4480. Min Act: -0.1700
Data Index: 6611686 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19