Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2974 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6852. Min Range: -7.6852
Max Act: 7.6852. Min Act: -0.1700
Data Index: 3737219 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6852. Min Range: -7.6852
Max Act: 7.3414. Min Act: -0.1700
Data Index: 2973760 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6852. Min Range: -7.6852
Max Act: 7.1539. Min Act: -0.1700
Data Index: 7434915 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6852. Min Range: -7.6852
Max Act: 7.1227. Min Act: -0.1700
Data Index: 5844649 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6852. Min Range: -7.6852
Max Act: 7.0289. Min Act: -0.1700
Data Index: 7598505 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6852. Min Range: -7.6852
Max Act: 7.0602. Min Act: -0.1700
Data Index: 2886666 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6852. Min Range: -7.6852
Max Act: 7.0289. Min Act: -0.1700
Data Index: 4339316 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6852. Min Range: -7.6852
Max Act: 6.9977. Min Act: -0.1700
Data Index: 826314 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6852. Min Range: -7.6852
Max Act: 6.9664. Min Act: -0.1700
Data Index: 7924460 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6852. Min Range: -7.6852
Max Act: 6.9352. Min Act: -0.1700
Data Index: 6403976 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6852. Min Range: -7.6852
Max Act: 6.9352. Min Act: -0.1700
Data Index: 2241490 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6852. Min Range: -7.6852
Max Act: 6.9039. Min Act: -0.1700
Data Index: 894834 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6852. Min Range: -7.6852
Max Act: 6.9039. Min Act: -0.1700
Data Index: 1862659 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6852. Min Range: -7.6852
Max Act: 6.8727. Min Act: -0.1700
Data Index: 5330049 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6852. Min Range: -7.6852
Max Act: 6.8414. Min Act: -0.1700
Data Index: 5860004 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6852. Min Range: -7.6852
Max Act: 6.8727. Min Act: -0.1700
Data Index: 5857998 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6852. Min Range: -7.6852
Max Act: 6.8414. Min Act: -0.1700
Data Index: 284372 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6852. Min Range: -7.6852
Max Act: 6.8102. Min Act: -0.1700
Data Index: 3828596 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6852. Min Range: -7.6852
Max Act: 6.8414. Min Act: -0.1700
Data Index: 1568843 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6852. Min Range: -7.6852
Max Act: 6.8102. Min Act: -0.1700
Data Index: 6263924 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19