Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2112 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2697. Min Range: -4.2697
Max Act: 4.2697. Min Act: -0.1700
Data Index: 8736645 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2697. Min Range: -4.2697
Max Act: 4.1447. Min Act: -0.1700
Data Index: 1222128 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2697. Min Range: -4.2697
Max Act: 4.1447. Min Act: -0.1700
Data Index: 1868096 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2697. Min Range: -4.2697
Max Act: 4.1134. Min Act: -0.1700
Data Index: 2396741 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2697. Min Range: -4.2697
Max Act: 4.0822. Min Act: -0.1700
Data Index: 8017089 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2697. Min Range: -4.2697
Max Act: 4.0822. Min Act: -0.1700
Data Index: 445855 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2697. Min Range: -4.2697
Max Act: 4.0822. Min Act: -0.1700
Data Index: 3807857 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2697. Min Range: -4.2697
Max Act: 4.0509. Min Act: -0.1700
Data Index: 5640354 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2697. Min Range: -4.2697
Max Act: 3.9884. Min Act: -0.1700
Data Index: 2717814 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2697. Min Range: -4.2697
Max Act: 3.9884. Min Act: -0.1700
Data Index: 925353 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2697. Min Range: -4.2697
Max Act: 4.0197. Min Act: -0.1700
Data Index: 7633475 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2697. Min Range: -4.2697
Max Act: 3.9884. Min Act: -0.1700
Data Index: 5638205 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2697. Min Range: -4.2697
Max Act: 4.0197. Min Act: -0.1700
Data Index: 1161415 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2697. Min Range: -4.2697
Max Act: 3.9884. Min Act: -0.1700
Data Index: 4634329 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2697. Min Range: -4.2697
Max Act: 3.9571. Min Act: -0.1700
Data Index: 2520423 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2697. Min Range: -4.2697
Max Act: 3.9571. Min Act: -0.1700
Data Index: 3788504 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2697. Min Range: -4.2697
Max Act: 3.9259. Min Act: -0.1700
Data Index: 3445092 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2697. Min Range: -4.2697
Max Act: 3.9571. Min Act: -0.1700
Data Index: 7819503 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2697. Min Range: -4.2697
Max Act: 3.9571. Min Act: -0.1700
Data Index: 1061671 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2697. Min Range: -4.2697
Max Act: 3.9259. Min Act: -0.1700
Data Index: 7296088 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19