Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2971 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0585. Min Range: -6.0585
Max Act: 6.0585. Min Act: -0.1700
Data Index: 8425486 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0585. Min Range: -6.0585
Max Act: 5.9022. Min Act: -0.1700
Data Index: 570487 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0585. Min Range: -6.0585
Max Act: 5.8710. Min Act: -0.1700
Data Index: 8066859 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0585. Min Range: -6.0585
Max Act: 5.8085. Min Act: -0.1700
Data Index: 3170044 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0585. Min Range: -6.0585
Max Act: 5.6522. Min Act: -0.1700
Data Index: 1982423 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0585. Min Range: -6.0585
Max Act: 5.6522. Min Act: -0.1700
Data Index: 4041461 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0585. Min Range: -6.0585
Max Act: 5.6210. Min Act: -0.1700
Data Index: 1026950 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0585. Min Range: -6.0585
Max Act: 5.5585. Min Act: -0.1700
Data Index: 7237036 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0585. Min Range: -6.0585
Max Act: 5.5272. Min Act: -0.1700
Data Index: 5726166 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0585. Min Range: -6.0585
Max Act: 5.5585. Min Act: -0.1700
Data Index: 2098516 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0585. Min Range: -6.0585
Max Act: 5.5272. Min Act: -0.1700
Data Index: 4768455 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0585. Min Range: -6.0585
Max Act: 5.4960. Min Act: -0.1700
Data Index: 3431864 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0585. Min Range: -6.0585
Max Act: 5.4960. Min Act: -0.1700
Data Index: 2409118 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0585. Min Range: -6.0585
Max Act: 5.4647. Min Act: -0.1700
Data Index: 1036997 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0585. Min Range: -6.0585
Max Act: 5.4647. Min Act: -0.1700
Data Index: 5201856 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0585. Min Range: -6.0585
Max Act: 5.4647. Min Act: -0.1700
Data Index: 8066855 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0585. Min Range: -6.0585
Max Act: 5.4647. Min Act: -0.1700
Data Index: 8440262 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0585. Min Range: -6.0585
Max Act: 5.4647. Min Act: -0.1700
Data Index: 340982 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0585. Min Range: -6.0585
Max Act: 5.4335. Min Act: -0.1700
Data Index: 6552514 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0585. Min Range: -6.0585
Max Act: 5.4335. Min Act: -0.1700
Data Index: 1003255 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19