Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 656 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2044. Min Range: -4.2044
Max Act: 4.2044. Min Act: -0.1700
Data Index: 3143446 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2044. Min Range: -4.2044
Max Act: 4.1732. Min Act: -0.1700
Data Index: 3143443 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2044. Min Range: -4.2044
Max Act: 4.1419. Min Act: -0.1700
Data Index: 2752464 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2044. Min Range: -4.2044
Max Act: 4.1107. Min Act: -0.1700
Data Index: 1298789 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2044. Min Range: -4.2044
Max Act: 4.0794. Min Act: -0.1700
Data Index: 3936516 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2044. Min Range: -4.2044
Max Act: 4.0169. Min Act: -0.1700
Data Index: 2307747 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2044. Min Range: -4.2044
Max Act: 3.9544. Min Act: -0.1700
Data Index: 4905954 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2044. Min Range: -4.2044
Max Act: 3.9231. Min Act: -0.1700
Data Index: 5956567 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2044. Min Range: -4.2044
Max Act: 3.8919. Min Act: -0.1700
Data Index: 4451517 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2044. Min Range: -4.2044
Max Act: 3.8919. Min Act: -0.1700
Data Index: 8332893 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2044. Min Range: -4.2044
Max Act: 3.8762. Min Act: -0.1700
Data Index: 4907473 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2044. Min Range: -4.2044
Max Act: 3.8137. Min Act: -0.1700
Data Index: 1033765 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2044. Min Range: -4.2044
Max Act: 3.8450. Min Act: -0.1700
Data Index: 4963852 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2044. Min Range: -4.2044
Max Act: 3.8137. Min Act: -0.1700
Data Index: 6517872 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2044. Min Range: -4.2044
Max Act: 3.8293. Min Act: -0.1700
Data Index: 7318319 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2044. Min Range: -4.2044
Max Act: 3.8137. Min Act: -0.1700
Data Index: 5229641 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2044. Min Range: -4.2044
Max Act: 3.7980. Min Act: -0.1700
Data Index: 3687252 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2044. Min Range: -4.2044
Max Act: 3.7668. Min Act: -0.1700
Data Index: 3517338 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2044. Min Range: -4.2044
Max Act: 3.7511. Min Act: -0.1700
Data Index: 863262 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2044. Min Range: -4.2044
Max Act: 3.7668. Min Act: -0.1700
Data Index: 1483876 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19