Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1047 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2369. Min Range: -5.2369
Max Act: 5.2369. Min Act: -0.1700
Data Index: 4005201 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2369. Min Range: -5.2369
Max Act: 5.1744. Min Act: -0.1700
Data Index: 5147754 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2369. Min Range: -5.2369
Max Act: 5.0807. Min Act: -0.1700
Data Index: 7492731 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2369. Min Range: -5.2369
Max Act: 5.0182. Min Act: -0.1700
Data Index: 4505913 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2369. Min Range: -5.2369
Max Act: 4.9557. Min Act: -0.1700
Data Index: 3223435 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2369. Min Range: -5.2369
Max Act: 4.8932. Min Act: -0.1700
Data Index: 7343274 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2369. Min Range: -5.2369
Max Act: 4.7994. Min Act: -0.1700
Data Index: 8393057 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2369. Min Range: -5.2369
Max Act: 4.8307. Min Act: -0.1700
Data Index: 6332477 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2369. Min Range: -5.2369
Max Act: 4.6744. Min Act: -0.1700
Data Index: 2380466 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2369. Min Range: -5.2369
Max Act: 4.7057. Min Act: -0.1700
Data Index: 1828158 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2369. Min Range: -5.2369
Max Act: 4.7057. Min Act: -0.1700
Data Index: 1030479 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2369. Min Range: -5.2369
Max Act: 4.7057. Min Act: -0.1700
Data Index: 3460644 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2369. Min Range: -5.2369
Max Act: 4.7057. Min Act: -0.1700
Data Index: 1171002 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2369. Min Range: -5.2369
Max Act: 4.6744. Min Act: -0.1700
Data Index: 7374317 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2369. Min Range: -5.2369
Max Act: 4.6744. Min Act: -0.1700
Data Index: 1239417 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2369. Min Range: -5.2369
Max Act: 4.7057. Min Act: -0.1700
Data Index: 2009140 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2369. Min Range: -5.2369
Max Act: 4.6744. Min Act: -0.1700
Data Index: 610181 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2369. Min Range: -5.2369
Max Act: 4.6432. Min Act: -0.1700
Data Index: 7272765 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2369. Min Range: -5.2369
Max Act: 4.6119. Min Act: -0.1700
Data Index: 2323927 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2369. Min Range: -5.2369
Max Act: 4.6119. Min Act: -0.1700
Data Index: 3867307 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19