Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2670 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0683. Min Range: -7.0683
Max Act: 7.0683. Min Act: -0.1700
Data Index: 6170858 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0683. Min Range: -7.0683
Max Act: 6.7245. Min Act: -0.1700
Data Index: 2990931 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0683. Min Range: -7.0683
Max Act: 6.6933. Min Act: -0.1700
Data Index: 3721545 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0683. Min Range: -7.0683
Max Act: 6.7558. Min Act: -0.1700
Data Index: 8719361 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0683. Min Range: -7.0683
Max Act: 6.7245. Min Act: -0.1700
Data Index: 824564 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0683. Min Range: -7.0683
Max Act: 6.6933. Min Act: -0.1700
Data Index: 300914 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0683. Min Range: -7.0683
Max Act: 6.5995. Min Act: -0.1700
Data Index: 3895457 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0683. Min Range: -7.0683
Max Act: 6.5995. Min Act: -0.1700
Data Index: 3721541 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0683. Min Range: -7.0683
Max Act: 6.4745. Min Act: -0.1700
Data Index: 2783623 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0683. Min Range: -7.0683
Max Act: 6.4745. Min Act: -0.1700
Data Index: 6087123 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0683. Min Range: -7.0683
Max Act: 6.4745. Min Act: -0.1700
Data Index: 8330797 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0683. Min Range: -7.0683
Max Act: 6.4433. Min Act: -0.1700
Data Index: 1819211 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0683. Min Range: -7.0683
Max Act: 6.4745. Min Act: -0.1700
Data Index: 300913 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0683. Min Range: -7.0683
Max Act: 6.3495. Min Act: -0.1699
Data Index: 3895479 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0683. Min Range: -7.0683
Max Act: 6.3808. Min Act: -0.1700
Data Index: 5479236 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0683. Min Range: -7.0683
Max Act: 6.3808. Min Act: -0.1700
Data Index: 3142249 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0683. Min Range: -7.0683
Max Act: 6.4120. Min Act: -0.1700
Data Index: 2027518 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0683. Min Range: -7.0683
Max Act: 6.3495. Min Act: -0.1700
Data Index: 1224417 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0683. Min Range: -7.0683
Max Act: 6.3495. Min Act: -0.1700
Data Index: 709327 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0683. Min Range: -7.0683
Max Act: 6.3183. Min Act: -0.1700
Data Index: 3895487 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19