Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3882 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.3399. Min Act: -0.1700
Data Index: 7250702 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.3087. Min Act: -0.1700
Data Index: 8404075 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.3087. Min Act: -0.1700
Data Index: 1031659 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.3087. Min Act: -0.1700
Data Index: 2743550 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.2774. Min Act: -0.1700
Data Index: 2026710 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.3087. Min Act: -0.1700
Data Index: 2701530 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.2149. Min Act: -0.1700
Data Index: 2445430 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.2462. Min Act: -0.1700
Data Index: 1580427 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.2462. Min Act: -0.1700
Data Index: 559593 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.2149. Min Act: -0.1700
Data Index: 2590372 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.2149. Min Act: -0.1700
Data Index: 438888 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.2149. Min Act: -0.1700
Data Index: 1062014 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.2462. Min Act: -0.1700
Data Index: 6778930 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.1837. Min Act: -0.1700
Data Index: 5383264 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.1837. Min Act: -0.1700
Data Index: 407133 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.1837. Min Act: -0.1700
Data Index: 7613813 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.1837. Min Act: -0.1700
Data Index: 684521 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.1837. Min Act: -0.1700
Data Index: 6512593 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.1837. Min Act: -0.1700
Data Index: 5492011 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.1837. Min Act: -0.1700
Data Index: 8077726 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19