Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2559 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0917. Min Range: -6.0917
Max Act: 6.0917. Min Act: -0.1700
Data Index: 2832217 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0917. Min Range: -6.0917
Max Act: 6.0292. Min Act: -0.1700
Data Index: 7678175 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0917. Min Range: -6.0917
Max Act: 5.8730. Min Act: -0.1700
Data Index: 3180298 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0917. Min Range: -6.0917
Max Act: 5.8730. Min Act: -0.1700
Data Index: 2445632 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0917. Min Range: -6.0917
Max Act: 5.8105. Min Act: -0.1700
Data Index: 5571385 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0917. Min Range: -6.0917
Max Act: 5.8417. Min Act: -0.1700
Data Index: 6985061 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0917. Min Range: -6.0917
Max Act: 5.8105. Min Act: -0.1700
Data Index: 5017652 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0917. Min Range: -6.0917
Max Act: 5.8105. Min Act: -0.1700
Data Index: 3495630 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0917. Min Range: -6.0917
Max Act: 5.7792. Min Act: -0.1700
Data Index: 2672861 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0917. Min Range: -6.0917
Max Act: 5.7480. Min Act: -0.1700
Data Index: 1201048 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0917. Min Range: -6.0917
Max Act: 5.7792. Min Act: -0.1700
Data Index: 8728202 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0917. Min Range: -6.0917
Max Act: 5.7480. Min Act: -0.1700
Data Index: 2825024 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0917. Min Range: -6.0917
Max Act: 5.7480. Min Act: -0.1700
Data Index: 8817897 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0917. Min Range: -6.0917
Max Act: 5.7480. Min Act: -0.1700
Data Index: 4387748 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0917. Min Range: -6.0917
Max Act: 5.7167. Min Act: -0.1700
Data Index: 5413704 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0917. Min Range: -6.0917
Max Act: 5.7480. Min Act: -0.1700
Data Index: 7114461 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0917. Min Range: -6.0917
Max Act: 5.7167. Min Act: -0.1700
Data Index: 4575980 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0917. Min Range: -6.0917
Max Act: 5.7167. Min Act: -0.1700
Data Index: 2319391 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0917. Min Range: -6.0917
Max Act: 5.7167. Min Act: -0.1700
Data Index: 8136952 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0917. Min Range: -6.0917
Max Act: 5.6855. Min Act: -0.1700
Data Index: 2346489 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19