Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1066 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.9691. Min Range: -7.9691
Max Act: 7.9691. Min Act: -0.1700
Data Index: 2770750 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9691. Min Range: -7.9691
Max Act: 7.9066. Min Act: -0.1700
Data Index: 252096 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9691. Min Range: -7.9691
Max Act: 7.8754. Min Act: -0.1700
Data Index: 605625 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9691. Min Range: -7.9691
Max Act: 7.8441. Min Act: -0.1700
Data Index: 5182977 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9691. Min Range: -7.9691
Max Act: 7.7816. Min Act: -0.1700
Data Index: 4119943 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9691. Min Range: -7.9691
Max Act: 7.7816. Min Act: -0.1700
Data Index: 177588 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9691. Min Range: -7.9691
Max Act: 7.6566. Min Act: -0.1700
Data Index: 4433094 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9691. Min Range: -7.9691
Max Act: 7.6254. Min Act: -0.1700
Data Index: 3047990 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9691. Min Range: -7.9691
Max Act: 7.6254. Min Act: -0.1700
Data Index: 3617346 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9691. Min Range: -7.9691
Max Act: 7.5941. Min Act: -0.1700
Data Index: 4338774 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9691. Min Range: -7.9691
Max Act: 7.5004. Min Act: -0.1700
Data Index: 4671993 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9691. Min Range: -7.9691
Max Act: 7.4379. Min Act: -0.1700
Data Index: 2678993 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9691. Min Range: -7.9691
Max Act: 7.4379. Min Act: -0.1700
Data Index: 2700128 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9691. Min Range: -7.9691
Max Act: 7.4379. Min Act: -0.1700
Data Index: 3977973 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9691. Min Range: -7.9691
Max Act: 7.4379. Min Act: -0.1700
Data Index: 3092623 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9691. Min Range: -7.9691
Max Act: 7.4066. Min Act: -0.1700
Data Index: 37331 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9691. Min Range: -7.9691
Max Act: 7.4066. Min Act: -0.1700
Data Index: 651272 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9691. Min Range: -7.9691
Max Act: 7.3129. Min Act: -0.1700
Data Index: 6902058 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9691. Min Range: -7.9691
Max Act: 7.2504. Min Act: -0.1700
Data Index: 1425238 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9691. Min Range: -7.9691
Max Act: 7.3129. Min Act: -0.1700
Data Index: 8509814 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #19