Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4472 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4603. Min Range: -4.4603
Max Act: 4.4603. Min Act: -0.1700
Data Index: 5542519 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4603. Min Range: -4.4603
Max Act: 4.3978. Min Act: -0.1694
Data Index: 2104871 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4603. Min Range: -4.4603
Max Act: 4.3353. Min Act: -0.1700
Data Index: 300626 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4603. Min Range: -4.4603
Max Act: 4.3040. Min Act: -0.1700
Data Index: 157802 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4603. Min Range: -4.4603
Max Act: 4.3040. Min Act: -0.1700
Data Index: 4159540 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4603. Min Range: -4.4603
Max Act: 4.3040. Min Act: -0.1700
Data Index: 3063543 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4603. Min Range: -4.4603
Max Act: 4.2728. Min Act: -0.1700
Data Index: 829092 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4603. Min Range: -4.4603
Max Act: 4.2728. Min Act: -0.1700
Data Index: 5363959 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4603. Min Range: -4.4603
Max Act: 4.2728. Min Act: -0.1700
Data Index: 5764013 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4603. Min Range: -4.4603
Max Act: 4.2728. Min Act: -0.1700
Data Index: 6334779 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4603. Min Range: -4.4603
Max Act: 4.2415. Min Act: -0.1700
Data Index: 3758835 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4603. Min Range: -4.4603
Max Act: 4.2415. Min Act: -0.1700
Data Index: 3146357 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4603. Min Range: -4.4603
Max Act: 4.2415. Min Act: -0.1700
Data Index: 3113314 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4603. Min Range: -4.4603
Max Act: 4.2415. Min Act: -0.1700
Data Index: 1393212 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4603. Min Range: -4.4603
Max Act: 4.2415. Min Act: -0.1697
Data Index: 5216366 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4603. Min Range: -4.4603
Max Act: 4.2415. Min Act: -0.1700
Data Index: 7470491 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4603. Min Range: -4.4603
Max Act: 4.2103. Min Act: -0.1700
Data Index: 725317 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4603. Min Range: -4.4603
Max Act: 4.2103. Min Act: -0.1700
Data Index: 6208331 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4603. Min Range: -4.4603
Max Act: 4.1790. Min Act: -0.1700
Data Index: 1828910 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4603. Min Range: -4.4603
Max Act: 4.2103. Min Act: -0.1697
Data Index: 2264716 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19