Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4680 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1443. Min Range: -7.1443
Max Act: 7.1443. Min Act: -0.1700
Data Index: 916032 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1443. Min Range: -7.1443
Max Act: 7.0193. Min Act: -0.1700
Data Index: 4268327 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.9568. Min Act: -0.1700
Data Index: 710971 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.8943. Min Act: -0.1700
Data Index: 2385417 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.8943. Min Act: -0.1700
Data Index: 3930392 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.8318. Min Act: -0.1700
Data Index: 2767326 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.8318. Min Act: -0.1700
Data Index: 7705051 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.8005. Min Act: -0.1700
Data Index: 1382155 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.7693. Min Act: -0.1700
Data Index: 4801573 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.7380. Min Act: -0.1700
Data Index: 4839898 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.7693. Min Act: -0.1700
Data Index: 360838 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.7380. Min Act: -0.1700
Data Index: 8313076 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.8005. Min Act: -0.1700
Data Index: 1975238 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.7693. Min Act: -0.1700
Data Index: 1901585 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.7380. Min Act: -0.1700
Data Index: 7612787 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.7380. Min Act: -0.1700
Data Index: 5747959 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.7068. Min Act: -0.1700
Data Index: 7669312 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.7068. Min Act: -0.1700
Data Index: 8735218 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.7068. Min Act: -0.1700
Data Index: 2778728 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1443. Min Range: -7.1443
Max Act: 6.7068. Min Act: -0.1700
Data Index: 7025080 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19