Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4044 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0542. Min Range: -8.0542
Max Act: 8.0542. Min Act: -0.1700
Data Index: 4891311 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0542. Min Range: -8.0542
Max Act: 7.6167. Min Act: -0.1700
Data Index: 4398906 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0542. Min Range: -8.0542
Max Act: 7.5542. Min Act: -0.1700
Data Index: 673374 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0542. Min Range: -8.0542
Max Act: 7.2730. Min Act: -0.1700
Data Index: 4811007 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0542. Min Range: -8.0542
Max Act: 7.2730. Min Act: -0.1700
Data Index: 683544 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0542. Min Range: -8.0542
Max Act: 7.2417. Min Act: -0.1700
Data Index: 1911129 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0542. Min Range: -8.0542
Max Act: 7.2417. Min Act: -0.1700
Data Index: 5908081 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0542. Min Range: -8.0542
Max Act: 7.2417. Min Act: -0.1700
Data Index: 6783372 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0542. Min Range: -8.0542
Max Act: 7.2417. Min Act: -0.1700
Data Index: 6958270 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0542. Min Range: -8.0542
Max Act: 7.2105. Min Act: -0.1700
Data Index: 7443927 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0542. Min Range: -8.0542
Max Act: 7.1792. Min Act: -0.1700
Data Index: 619047 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0542. Min Range: -8.0542
Max Act: 7.1480. Min Act: -0.1700
Data Index: 3195153 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0542. Min Range: -8.0542
Max Act: 7.1480. Min Act: -0.1700
Data Index: 7406700 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0542. Min Range: -8.0542
Max Act: 7.1480. Min Act: -0.1700
Data Index: 5040391 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0542. Min Range: -8.0542
Max Act: 7.0855. Min Act: -0.1700
Data Index: 7611166 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0542. Min Range: -8.0542
Max Act: 7.0542. Min Act: -0.1700
Data Index: 2619523 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0542. Min Range: -8.0542
Max Act: 7.0542. Min Act: -0.1700
Data Index: 2865759 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0542. Min Range: -8.0542
Max Act: 7.0542. Min Act: -0.1700
Data Index: 2489915 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0542. Min Range: -8.0542
Max Act: 7.0230. Min Act: -0.1700
Data Index: 3845114 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0542. Min Range: -8.0542
Max Act: 7.0230. Min Act: -0.1700
Data Index: 7583858 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19