Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3108 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5600. Min Range: -3.5600
Max Act: 3.5600. Min Act: -0.1700
Data Index: 1718245 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5600. Min Range: -3.5600
Max Act: 3.5600. Min Act: -0.1700
Data Index: 4037101 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5600. Min Range: -3.5600
Max Act: 3.5130. Min Act: -0.1700
Data Index: 4570797 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5600. Min Range: -3.5600
Max Act: 3.4974. Min Act: -0.1700
Data Index: 2271411 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5600. Min Range: -3.5600
Max Act: 3.4817. Min Act: -0.1700
Data Index: 3348092 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5600. Min Range: -3.5600
Max Act: 3.4817. Min Act: -0.1700
Data Index: 70651 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5600. Min Range: -3.5600
Max Act: 3.4660. Min Act: -0.1700
Data Index: 1884999 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5600. Min Range: -3.5600
Max Act: 3.4660. Min Act: -0.1700
Data Index: 1104111 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5600. Min Range: -3.5600
Max Act: 3.4660. Min Act: -0.1700
Data Index: 1622267 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5600. Min Range: -3.5600
Max Act: 3.4504. Min Act: -0.1700
Data Index: 7453765 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5600. Min Range: -3.5600
Max Act: 3.4033. Min Act: -0.1700
Data Index: 704678 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5600. Min Range: -3.5600
Max Act: 3.4190. Min Act: -0.1700
Data Index: 7215156 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5600. Min Range: -3.5600
Max Act: 3.4347. Min Act: -0.1700
Data Index: 1699101 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5600. Min Range: -3.5600
Max Act: 3.3877. Min Act: -0.1700
Data Index: 1929683 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5600. Min Range: -3.5600
Max Act: 3.3877. Min Act: -0.1700
Data Index: 8222204 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5600. Min Range: -3.5600
Max Act: 3.3877. Min Act: -0.1700
Data Index: 1544389 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5600. Min Range: -3.5600
Max Act: 3.3877. Min Act: -0.1700
Data Index: 5250735 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5600. Min Range: -3.5600
Max Act: 3.3563. Min Act: -0.1700
Data Index: 2711543 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5600. Min Range: -3.5600
Max Act: 3.3720. Min Act: -0.1700
Data Index: 638608 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5600. Min Range: -3.5600
Max Act: 3.3720. Min Act: -0.1700
Data Index: 803080 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19