Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 717 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.6947. Min Act: -0.1700
Data Index: 7461172 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.6322. Min Act: -0.1700
Data Index: 4586607 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.6010. Min Act: -0.1700
Data Index: 3936563 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.6010. Min Act: -0.1700
Data Index: 4977953 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.6010. Min Act: -0.1700
Data Index: 2441261 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.5697. Min Act: -0.1700
Data Index: 8078518 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.5697. Min Act: -0.1700
Data Index: 2844687 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.5385. Min Act: -0.1700
Data Index: 260503 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.5072. Min Act: -0.1700
Data Index: 4007610 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.5072. Min Act: -0.1700
Data Index: 6330647 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.5072. Min Act: -0.1700
Data Index: 5805451 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.5072. Min Act: -0.1700
Data Index: 3936562 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.4760. Min Act: -0.1700
Data Index: 8679289 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.4447. Min Act: -0.1700
Data Index: 196853 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.4135. Min Act: -0.1700
Data Index: 3561519 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.4447. Min Act: -0.1700
Data Index: 7561804 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.3822. Min Act: -0.1700
Data Index: 189144 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.4135. Min Act: -0.1700
Data Index: 3863306 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.3510. Min Act: -0.1700
Data Index: 1565906 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6947. Min Range: -5.6947
Max Act: 5.3822. Min Act: -0.1700
Data Index: 3668144 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19