Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3385 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.6222. Min Range: -11.6222
Max Act: 11.6222. Min Act: -0.1700
Data Index: 3105360 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.6222. Min Range: -11.6222
Max Act: 11.1847. Min Act: -0.1700
Data Index: 7427761 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.6222. Min Range: -11.6222
Max Act: 11.1222. Min Act: -0.1700
Data Index: 2760442 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.6222. Min Range: -11.6222
Max Act: 11.0597. Min Act: -0.1700
Data Index: 6408876 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.6222. Min Range: -11.6222
Max Act: 10.9972. Min Act: -0.1700
Data Index: 4952846 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.6222. Min Range: -11.6222
Max Act: 10.9347. Min Act: -0.1700
Data Index: 7183385 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.6222. Min Range: -11.6222
Max Act: 10.8097. Min Act: -0.1700
Data Index: 3120692 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.6222. Min Range: -11.6222
Max Act: 10.6847. Min Act: -0.1700
Data Index: 4878648 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.6222. Min Range: -11.6222
Max Act: 10.6847. Min Act: -0.1700
Data Index: 5774252 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.6222. Min Range: -11.6222
Max Act: 10.6222. Min Act: -0.1700
Data Index: 8295705 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.6222. Min Range: -11.6222
Max Act: 10.6222. Min Act: -0.1700
Data Index: 1149343 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.6222. Min Range: -11.6222
Max Act: 10.5597. Min Act: -0.1700
Data Index: 7539892 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.6222. Min Range: -11.6222
Max Act: 10.5597. Min Act: -0.1700
Data Index: 696123 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.6222. Min Range: -11.6222
Max Act: 10.5597. Min Act: -0.1700
Data Index: 4327303 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.6222. Min Range: -11.6222
Max Act: 10.5597. Min Act: -0.1700
Data Index: 7846976 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.6222. Min Range: -11.6222
Max Act: 10.5597. Min Act: -0.1700
Data Index: 7678621 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.6222. Min Range: -11.6222
Max Act: 10.4972. Min Act: -0.1700
Data Index: 2797822 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.6222. Min Range: -11.6222
Max Act: 10.4347. Min Act: -0.1700
Data Index: 4568833 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.6222. Min Range: -11.6222
Max Act: 10.4347. Min Act: -0.1700
Data Index: 2305968 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.6222. Min Range: -11.6222
Max Act: 10.3722. Min Act: -0.1700
Data Index: 1413667 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19