Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5200 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2791. Min Range: -8.2791
Max Act: 8.2791. Min Act: -0.1700
Data Index: 1221204 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2791. Min Range: -8.2791
Max Act: 8.0916. Min Act: -0.1700
Data Index: 568200 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2791. Min Range: -8.2791
Max Act: 8.0916. Min Act: -0.1700
Data Index: 8321711 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2791. Min Range: -8.2791
Max Act: 7.9666. Min Act: -0.1700
Data Index: 5712997 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2791. Min Range: -8.2791
Max Act: 7.8416. Min Act: -0.1700
Data Index: 1209968 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2791. Min Range: -8.2791
Max Act: 7.8416. Min Act: -0.1700
Data Index: 5058884 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2791. Min Range: -8.2791
Max Act: 7.7166. Min Act: -0.1700
Data Index: 8578387 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2791. Min Range: -8.2791
Max Act: 7.7478. Min Act: -0.1700
Data Index: 2017027 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2791. Min Range: -8.2791
Max Act: 7.7166. Min Act: -0.1700
Data Index: 2612384 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2791. Min Range: -8.2791
Max Act: 7.7166. Min Act: -0.1700
Data Index: 5358205 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2791. Min Range: -8.2791
Max Act: 7.5916. Min Act: -0.1700
Data Index: 315918 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2791. Min Range: -8.2791
Max Act: 7.5916. Min Act: -0.1700
Data Index: 8631294 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2791. Min Range: -8.2791
Max Act: 7.5603. Min Act: -0.1700
Data Index: 8651687 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2791. Min Range: -8.2791
Max Act: 7.5603. Min Act: -0.1700
Data Index: 2808807 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2791. Min Range: -8.2791
Max Act: 7.5291. Min Act: -0.1700
Data Index: 3622952 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2791. Min Range: -8.2791
Max Act: 7.5291. Min Act: -0.1700
Data Index: 6013019 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2791. Min Range: -8.2791
Max Act: 7.4978. Min Act: -0.1700
Data Index: 1606461 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2791. Min Range: -8.2791
Max Act: 7.4666. Min Act: -0.1700
Data Index: 3398757 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2791. Min Range: -8.2791
Max Act: 7.4353. Min Act: -0.1700
Data Index: 8237416 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2791. Min Range: -8.2791
Max Act: 7.4353. Min Act: -0.1700
Data Index: 1660873 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19