Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1228 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1038. Min Range: -4.1038
Max Act: 4.1038. Min Act: -0.1700
Data Index: 960200 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1038. Min Range: -4.1038
Max Act: 4.0413. Min Act: -0.1700
Data Index: 5867899 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1038. Min Range: -4.1038
Max Act: 4.0413. Min Act: -0.1700
Data Index: 253753 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1038. Min Range: -4.1038
Max Act: 4.0100. Min Act: -0.1700
Data Index: 4953895 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1038. Min Range: -4.1038
Max Act: 3.9788. Min Act: -0.1700
Data Index: 6521610 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1038. Min Range: -4.1038
Max Act: 3.9788. Min Act: -0.1700
Data Index: 3922253 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1038. Min Range: -4.1038
Max Act: 3.9475. Min Act: -0.1700
Data Index: 8538020 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1038. Min Range: -4.1038
Max Act: 3.9162. Min Act: -0.1700
Data Index: 1109690 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1038. Min Range: -4.1038
Max Act: 3.8850. Min Act: -0.1700
Data Index: 6177428 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1038. Min Range: -4.1038
Max Act: 3.8850. Min Act: -0.1700
Data Index: 1919118 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1038. Min Range: -4.1038
Max Act: 3.8537. Min Act: -0.1700
Data Index: 3785447 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1038. Min Range: -4.1038
Max Act: 3.8537. Min Act: -0.1700
Data Index: 2882429 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1038. Min Range: -4.1038
Max Act: 3.8537. Min Act: -0.1700
Data Index: 1124884 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1038. Min Range: -4.1038
Max Act: 3.8537. Min Act: -0.1700
Data Index: 4258163 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1038. Min Range: -4.1038
Max Act: 3.8537. Min Act: -0.1700
Data Index: 3415633 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1038. Min Range: -4.1038
Max Act: 3.8537. Min Act: -0.1700
Data Index: 4212497 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1038. Min Range: -4.1038
Max Act: 3.8537. Min Act: -0.1700
Data Index: 2442863 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1038. Min Range: -4.1038
Max Act: 3.8224. Min Act: -0.1700
Data Index: 4552749 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1038. Min Range: -4.1038
Max Act: 3.8224. Min Act: -0.1700
Data Index: 4716651 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1038. Min Range: -4.1038
Max Act: 3.8224. Min Act: -0.1700
Data Index: 2835569 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19