Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1956 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1953. Min Range: -7.1953
Max Act: 7.1328. Min Act: -0.1700
Data Index: 4458810 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1953. Min Range: -7.1953
Max Act: 7.1953. Min Act: -0.1700
Data Index: 460510 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1953. Min Range: -7.1953
Max Act: 7.1953. Min Act: -0.1700
Data Index: 2555686 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1953. Min Range: -7.1953
Max Act: 7.0703. Min Act: -0.1700
Data Index: 763770 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1953. Min Range: -7.1953
Max Act: 7.0703. Min Act: -0.1700
Data Index: 7809295 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1953. Min Range: -7.1953
Max Act: 7.0703. Min Act: -0.1700
Data Index: 7258877 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.9453. Min Act: -0.1700
Data Index: 7522992 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.9140. Min Act: -0.1700
Data Index: 5809285 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.8828. Min Act: -0.1700
Data Index: 936400 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.8828. Min Act: -0.1700
Data Index: 404426 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.8515. Min Act: -0.1700
Data Index: 6147101 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.7890. Min Act: -0.1700
Data Index: 2227972 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.7890. Min Act: -0.1700
Data Index: 5669651 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.7890. Min Act: -0.1700
Data Index: 21238 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.7890. Min Act: -0.1700
Data Index: 6886153 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.7578. Min Act: -0.1700
Data Index: 3091940 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.7578. Min Act: -0.1700
Data Index: 1295575 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.7578. Min Act: -0.1700
Data Index: 5956349 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.7578. Min Act: -0.1700
Data Index: 1909222 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1953. Min Range: -7.1953
Max Act: 6.7578. Min Act: -0.1700
Data Index: 21833 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19