Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2787 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1934. Min Range: -3.1934
Max Act: 3.1776. Min Act: -0.1700
Data Index: 7018527 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1934. Min Range: -3.1934
Max Act: 3.1934. Min Act: -0.1700
Data Index: 5933329 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1934. Min Range: -3.1934
Max Act: 3.1147. Min Act: -0.1700
Data Index: 6316682 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1934. Min Range: -3.1934
Max Act: 3.1147. Min Act: -0.1700
Data Index: 4168958 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1934. Min Range: -3.1934
Max Act: 3.0674. Min Act: -0.1700
Data Index: 7018504 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1934. Min Range: -3.1934
Max Act: 3.0674. Min Act: -0.1700
Data Index: 2698722 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1934. Min Range: -3.1934
Max Act: 3.0358. Min Act: -0.1700
Data Index: 19941 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1934. Min Range: -3.1934
Max Act: 3.0200. Min Act: -0.1700
Data Index: 7018516 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1934. Min Range: -3.1934
Max Act: 3.0358. Min Act: -0.1700
Data Index: 6297864 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1934. Min Range: -3.1934
Max Act: 3.0358. Min Act: -0.1700
Data Index: 7018506 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1934. Min Range: -3.1934
Max Act: 3.0200. Min Act: -0.1700
Data Index: 1911140 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1934. Min Range: -3.1934
Max Act: 3.0200. Min Act: -0.1700
Data Index: 7018517 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1934. Min Range: -3.1934
Max Act: 3.0358. Min Act: -0.1700
Data Index: 3211144 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1934. Min Range: -3.1934
Max Act: 3.0042. Min Act: -0.1700
Data Index: 3973521 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1934. Min Range: -3.1934
Max Act: 3.0042. Min Act: -0.1700
Data Index: 5351077 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1934. Min Range: -3.1934
Max Act: 2.9726. Min Act: -0.1700
Data Index: 7018526 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1934. Min Range: -3.1934
Max Act: 2.9884. Min Act: -0.1700
Data Index: 5025437 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1934. Min Range: -3.1934
Max Act: 2.9884. Min Act: -0.1700
Data Index: 7545270 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1934. Min Range: -3.1934
Max Act: 2.9726. Min Act: -0.1700
Data Index: 2649723 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1934. Min Range: -3.1934
Max Act: 2.9568. Min Act: -0.1700
Data Index: 4971877 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19