Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3338 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8486. Min Range: -4.8486
Max Act: 4.8486. Min Act: -0.1700
Data Index: 8731888 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8486. Min Range: -4.8486
Max Act: 4.7548. Min Act: -0.1700
Data Index: 5646900 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8486. Min Range: -4.8486
Max Act: 4.7861. Min Act: -0.1700
Data Index: 8665718 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8486. Min Range: -4.8486
Max Act: 4.7548. Min Act: -0.1700
Data Index: 4051349 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8486. Min Range: -4.8486
Max Act: 4.7236. Min Act: -0.1700
Data Index: 2562935 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8486. Min Range: -4.8486
Max Act: 4.6611. Min Act: -0.1668
Data Index: 2798952 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8486. Min Range: -4.8486
Max Act: 4.6611. Min Act: -0.1700
Data Index: 3332758 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8486. Min Range: -4.8486
Max Act: 4.6611. Min Act: -0.1696
Data Index: 676985 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8486. Min Range: -4.8486
Max Act: 4.6611. Min Act: -0.1700
Data Index: 7608934 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8486. Min Range: -4.8486
Max Act: 4.6298. Min Act: -0.1700
Data Index: 1269845 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8486. Min Range: -4.8486
Max Act: 4.6611. Min Act: -0.1700
Data Index: 3395810 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8486. Min Range: -4.8486
Max Act: 4.6298. Min Act: -0.1700
Data Index: 4940928 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8486. Min Range: -4.8486
Max Act: 4.6298. Min Act: -0.1700
Data Index: 7014247 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8486. Min Range: -4.8486
Max Act: 4.5986. Min Act: -0.1700
Data Index: 4498430 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8486. Min Range: -4.8486
Max Act: 4.5986. Min Act: -0.1700
Data Index: 2416883 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8486. Min Range: -4.8486
Max Act: 4.5986. Min Act: -0.1700
Data Index: 129875 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8486. Min Range: -4.8486
Max Act: 4.5986. Min Act: -0.1700
Data Index: 5010857 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8486. Min Range: -4.8486
Max Act: 4.5986. Min Act: -0.1700
Data Index: 5336070 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8486. Min Range: -4.8486
Max Act: 4.5986. Min Act: -0.1698
Data Index: 5548582 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8486. Min Range: -4.8486
Max Act: 4.5986. Min Act: -0.1700
Data Index: 5616253 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19