Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1673 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3401. Min Range: -5.3401
Max Act: 5.3401. Min Act: -0.1700
Data Index: 8078716 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3401. Min Range: -5.3401
Max Act: 5.2463. Min Act: -0.1700
Data Index: 3834158 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3401. Min Range: -5.3401
Max Act: 5.2151. Min Act: -0.1700
Data Index: 5794683 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3401. Min Range: -5.3401
Max Act: 5.2151. Min Act: -0.1700
Data Index: 2272142 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3401. Min Range: -5.3401
Max Act: 5.1838. Min Act: -0.1700
Data Index: 2179118 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3401. Min Range: -5.3401
Max Act: 5.1838. Min Act: -0.1700
Data Index: 4171962 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3401. Min Range: -5.3401
Max Act: 5.1838. Min Act: -0.1700
Data Index: 7972676 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3401. Min Range: -5.3401
Max Act: 5.1526. Min Act: -0.1700
Data Index: 3699943 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3401. Min Range: -5.3401
Max Act: 5.1526. Min Act: -0.1700
Data Index: 8289188 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3401. Min Range: -5.3401
Max Act: 5.0901. Min Act: -0.1700
Data Index: 1283219 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3401. Min Range: -5.3401
Max Act: 5.1213. Min Act: -0.1700
Data Index: 3785001 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3401. Min Range: -5.3401
Max Act: 5.1213. Min Act: -0.1700
Data Index: 2674993 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3401. Min Range: -5.3401
Max Act: 5.1213. Min Act: -0.1700
Data Index: 389848 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3401. Min Range: -5.3401
Max Act: 5.0901. Min Act: -0.1700
Data Index: 2085769 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3401. Min Range: -5.3401
Max Act: 5.0901. Min Act: -0.1700
Data Index: 5717069 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3401. Min Range: -5.3401
Max Act: 5.0901. Min Act: -0.1700
Data Index: 521745 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3401. Min Range: -5.3401
Max Act: 5.0588. Min Act: -0.1700
Data Index: 7948601 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3401. Min Range: -5.3401
Max Act: 5.0901. Min Act: -0.1700
Data Index: 3683770 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3401. Min Range: -5.3401
Max Act: 5.0588. Min Act: -0.1700
Data Index: 8553766 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3401. Min Range: -5.3401
Max Act: 5.0901. Min Act: -0.1700
Data Index: 8666525 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19