Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2595 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7468. Min Range: -5.7468
Max Act: 5.7468. Min Act: -0.1700
Data Index: 2822616 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7468. Min Range: -5.7468
Max Act: 5.7155. Min Act: -0.1700
Data Index: 7460290 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7468. Min Range: -5.7468
Max Act: 5.6843. Min Act: -0.1700
Data Index: 7460282 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7468. Min Range: -5.7468
Max Act: 5.5593. Min Act: -0.1700
Data Index: 2954025 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7468. Min Range: -5.7468
Max Act: 5.5593. Min Act: -0.1699
Data Index: 2097745 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7468. Min Range: -5.7468
Max Act: 5.4968. Min Act: -0.1700
Data Index: 5196675 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7468. Min Range: -5.7468
Max Act: 5.4968. Min Act: -0.1700
Data Index: 736747 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7468. Min Range: -5.7468
Max Act: 5.4655. Min Act: -0.1700
Data Index: 6660438 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7468. Min Range: -5.7468
Max Act: 5.4655. Min Act: -0.1700
Data Index: 4549147 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7468. Min Range: -5.7468
Max Act: 5.4343. Min Act: -0.1700
Data Index: 2695232 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7468. Min Range: -5.7468
Max Act: 5.4343. Min Act: -0.1700
Data Index: 7992057 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7468. Min Range: -5.7468
Max Act: 5.4343. Min Act: -0.1700
Data Index: 2793587 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7468. Min Range: -5.7468
Max Act: 5.4655. Min Act: -0.1700
Data Index: 6827650 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7468. Min Range: -5.7468
Max Act: 5.4343. Min Act: -0.1700
Data Index: 6733888 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7468. Min Range: -5.7468
Max Act: 5.4343. Min Act: -0.1700
Data Index: 5740931 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7468. Min Range: -5.7468
Max Act: 5.4343. Min Act: -0.1700
Data Index: 4018433 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7468. Min Range: -5.7468
Max Act: 5.4343. Min Act: -0.1700
Data Index: 2349492 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7468. Min Range: -5.7468
Max Act: 5.4030. Min Act: -0.1700
Data Index: 5269681 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7468. Min Range: -5.7468
Max Act: 5.3718. Min Act: -0.1700
Data Index: 4290746 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7468. Min Range: -5.7468
Max Act: 5.4030. Min Act: -0.1700
Data Index: 5579248 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19