Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3210 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.8699. Min Range: -1.8699
Max Act: 1.8699. Min Act: -0.1624
Data Index: 2439563 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8699. Min Range: -1.8699
Max Act: 1.8357. Min Act: -0.1681
Data Index: 6852705 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8699. Min Range: -1.8699
Max Act: 1.8271. Min Act: -0.1693
Data Index: 538428 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8699. Min Range: -1.8699
Max Act: 1.8271. Min Act: -0.1671
Data Index: 8633979 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8699. Min Range: -1.8699
Max Act: 1.8185. Min Act: -0.1675
Data Index: 7735917 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8699. Min Range: -1.8699
Max Act: 1.8099. Min Act: -0.1696
Data Index: 2155719 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8699. Min Range: -1.8699
Max Act: 1.8013. Min Act: -0.1622
Data Index: 8081217 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8699. Min Range: -1.8699
Max Act: 1.8013. Min Act: -0.1698
Data Index: 7802872 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8699. Min Range: -1.8699
Max Act: 1.8013. Min Act: -0.1700
Data Index: 7282627 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8699. Min Range: -1.8699
Max Act: 1.7927. Min Act: -0.1694
Data Index: 8209021 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8699. Min Range: -1.8699
Max Act: 1.7841. Min Act: -0.1675
Data Index: 2413085 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8699. Min Range: -1.8699
Max Act: 1.7669. Min Act: -0.1370
Data Index: 1745557 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8699. Min Range: -1.8699
Max Act: 1.7669. Min Act: -0.1667
Data Index: 2285514 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8699. Min Range: -1.8699
Max Act: 1.7669. Min Act: -0.1686
Data Index: 1597123 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8699. Min Range: -1.8699
Max Act: 1.7669. Min Act: -0.1700
Data Index: 1484544 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8699. Min Range: -1.8699
Max Act: 1.7669. Min Act: -0.1613
Data Index: 1719464 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8699. Min Range: -1.8699
Max Act: 1.7582. Min Act: -0.1665
Data Index: 2690693 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8699. Min Range: -1.8699
Max Act: 1.7582. Min Act: -0.1698
Data Index: 4986948 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8699. Min Range: -1.8699
Max Act: 1.7496. Min Act: -0.1700
Data Index: 7924075 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8699. Min Range: -1.8699
Max Act: 1.7582. Min Act: -0.1647
Data Index: 3998076 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19