Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4672 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5432. Min Range: -6.5432
Max Act: 6.5432. Min Act: -0.1700
Data Index: 4095550 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5432. Min Range: -6.5432
Max Act: 6.4182. Min Act: -0.1700
Data Index: 4095547 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5432. Min Range: -6.5432
Max Act: 6.2619. Min Act: -0.1700
Data Index: 1817876 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5432. Min Range: -6.5432
Max Act: 6.2307. Min Act: -0.1700
Data Index: 1688223 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5432. Min Range: -6.5432
Max Act: 6.2307. Min Act: -0.1700
Data Index: 8469425 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5432. Min Range: -6.5432
Max Act: 6.2307. Min Act: -0.1700
Data Index: 6222696 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5432. Min Range: -6.5432
Max Act: 6.1682. Min Act: -0.1700
Data Index: 4981139 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5432. Min Range: -6.5432
Max Act: 6.1369. Min Act: -0.1700
Data Index: 6625463 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5432. Min Range: -6.5432
Max Act: 6.1369. Min Act: -0.1700
Data Index: 4995446 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5432. Min Range: -6.5432
Max Act: 6.1369. Min Act: -0.1700
Data Index: 2236249 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5432. Min Range: -6.5432
Max Act: 6.1369. Min Act: -0.1700
Data Index: 8363824 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5432. Min Range: -6.5432
Max Act: 6.1057. Min Act: -0.1700
Data Index: 892314 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5432. Min Range: -6.5432
Max Act: 6.1057. Min Act: -0.1700
Data Index: 7591051 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5432. Min Range: -6.5432
Max Act: 6.1057. Min Act: -0.1700
Data Index: 2825460 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5432. Min Range: -6.5432
Max Act: 6.0744. Min Act: -0.1700
Data Index: 388827 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5432. Min Range: -6.5432
Max Act: 6.0744. Min Act: -0.1700
Data Index: 8363835 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5432. Min Range: -6.5432
Max Act: 6.0744. Min Act: -0.1700
Data Index: 5900968 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5432. Min Range: -6.5432
Max Act: 6.0744. Min Act: -0.1700
Data Index: 6789140 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5432. Min Range: -6.5432
Max Act: 6.0432. Min Act: -0.1700
Data Index: 2374615 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5432. Min Range: -6.5432
Max Act: 6.0432. Min Act: -0.1700
Data Index: 6222700 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19