Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2577 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.6961. Min Range: -0.6961
Max Act: 0.6961. Min Act: -0.1697
Data Index: 8190873 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6961. Min Range: -0.6961
Max Act: 0.6798. Min Act: -0.1689
Data Index: 3138502 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6961. Min Range: -0.6961
Max Act: 0.6717. Min Act: -0.1700
Data Index: 2184779 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6961. Min Range: -0.6961
Max Act: 0.6637. Min Act: -0.1700
Data Index: 2201911 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6961. Min Range: -0.6961
Max Act: 0.6717. Min Act: -0.1700
Data Index: 7138934 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6961. Min Range: -0.6961
Max Act: 0.6637. Min Act: -0.1699
Data Index: 8378816 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6961. Min Range: -0.6961
Max Act: 0.6637. Min Act: -0.1700
Data Index: 8403124 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6961. Min Range: -0.6961
Max Act: 0.6637. Min Act: -0.1700
Data Index: 3297411 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6961. Min Range: -0.6961
Max Act: 0.6556. Min Act: -0.1696
Data Index: 6789190 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6961. Min Range: -0.6961
Max Act: 0.6637. Min Act: -0.1687
Data Index: 5028564 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6961. Min Range: -0.6961
Max Act: 0.6637. Min Act: -0.1697
Data Index: 1887299 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6961. Min Range: -0.6961
Max Act: 0.6396. Min Act: -0.1688
Data Index: 2171499 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6961. Min Range: -0.6961
Max Act: 0.6556. Min Act: -0.1663
Data Index: 4871947 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6961. Min Range: -0.6961
Max Act: 0.6637. Min Act: -0.1698
Data Index: 6727175 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6961. Min Range: -0.6961
Max Act: 0.6556. Min Act: -0.1700
Data Index: 8757520 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6961. Min Range: -0.6961
Max Act: 0.6476. Min Act: -0.1700
Data Index: 6014524 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6961. Min Range: -0.6961
Max Act: 0.6556. Min Act: -0.1693
Data Index: 649542 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6961. Min Range: -0.6961
Max Act: 0.6396. Min Act: -0.1697
Data Index: 7276399 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6961. Min Range: -0.6961
Max Act: 0.6556. Min Act: -0.1700
Data Index: 7659418 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6961. Min Range: -0.6961
Max Act: 0.6396. Min Act: -0.1613
Data Index: 1176444 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19