Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4443 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0678. Min Range: -6.0678
Max Act: 6.0678. Min Act: -0.1700
Data Index: 3211291 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0678. Min Range: -6.0678
Max Act: 6.0053. Min Act: -0.1700
Data Index: 5060398 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0678. Min Range: -6.0678
Max Act: 5.8491. Min Act: -0.1700
Data Index: 7038192 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0678. Min Range: -6.0678
Max Act: 5.7866. Min Act: -0.1700
Data Index: 5796694 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0678. Min Range: -6.0678
Max Act: 5.7553. Min Act: -0.1700
Data Index: 7101429 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0678. Min Range: -6.0678
Max Act: 5.7553. Min Act: -0.1700
Data Index: 6769628 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0678. Min Range: -6.0678
Max Act: 5.7241. Min Act: -0.1700
Data Index: 8337273 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0678. Min Range: -6.0678
Max Act: 5.7241. Min Act: -0.1700
Data Index: 4545438 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0678. Min Range: -6.0678
Max Act: 5.6928. Min Act: -0.1700
Data Index: 5870892 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0678. Min Range: -6.0678
Max Act: 5.6616. Min Act: -0.1700
Data Index: 962737 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0678. Min Range: -6.0678
Max Act: 5.6928. Min Act: -0.1700
Data Index: 2494717 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0678. Min Range: -6.0678
Max Act: 5.6928. Min Act: -0.1700
Data Index: 6139869 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0678. Min Range: -6.0678
Max Act: 5.6303. Min Act: -0.1700
Data Index: 6032598 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0678. Min Range: -6.0678
Max Act: 5.5678. Min Act: -0.1700
Data Index: 5447620 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0678. Min Range: -6.0678
Max Act: 5.5678. Min Act: -0.1700
Data Index: 1708100 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0678. Min Range: -6.0678
Max Act: 5.5366. Min Act: -0.1700
Data Index: 4764895 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0678. Min Range: -6.0678
Max Act: 5.5366. Min Act: -0.1700
Data Index: 280107 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0678. Min Range: -6.0678
Max Act: 5.5678. Min Act: -0.1700
Data Index: 5635020 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0678. Min Range: -6.0678
Max Act: 5.5366. Min Act: -0.1700
Data Index: 1740941 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0678. Min Range: -6.0678
Max Act: 5.5053. Min Act: -0.1700
Data Index: 6970565 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19