Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2784 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3799. Min Range: -6.3799
Max Act: 6.3799. Min Act: -0.1700
Data Index: 1125814 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3799. Min Range: -6.3799
Max Act: 6.3799. Min Act: -0.1700
Data Index: 3759379 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3799. Min Range: -6.3799
Max Act: 6.3486. Min Act: -0.1700
Data Index: 8135928 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3799. Min Range: -6.3799
Max Act: 6.3486. Min Act: -0.1700
Data Index: 6931493 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3799. Min Range: -6.3799
Max Act: 6.2549. Min Act: -0.1700
Data Index: 5185458 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3799. Min Range: -6.3799
Max Act: 6.2549. Min Act: -0.1700
Data Index: 1321191 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3799. Min Range: -6.3799
Max Act: 6.2236. Min Act: -0.1700
Data Index: 4048377 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3799. Min Range: -6.3799
Max Act: 6.2549. Min Act: -0.1700
Data Index: 7319068 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3799. Min Range: -6.3799
Max Act: 6.2236. Min Act: -0.1700
Data Index: 6572269 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3799. Min Range: -6.3799
Max Act: 6.2236. Min Act: -0.1700
Data Index: 1288207 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3799. Min Range: -6.3799
Max Act: 6.2236. Min Act: -0.1700
Data Index: 4593527 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3799. Min Range: -6.3799
Max Act: 6.2236. Min Act: -0.1700
Data Index: 730888 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3799. Min Range: -6.3799
Max Act: 6.1924. Min Act: -0.1700
Data Index: 562589 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3799. Min Range: -6.3799
Max Act: 6.1924. Min Act: -0.1700
Data Index: 5368605 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3799. Min Range: -6.3799
Max Act: 6.1924. Min Act: -0.1700
Data Index: 4893699 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3799. Min Range: -6.3799
Max Act: 6.1611. Min Act: -0.1700
Data Index: 7542165 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3799. Min Range: -6.3799
Max Act: 6.1611. Min Act: -0.1700
Data Index: 260207 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3799. Min Range: -6.3799
Max Act: 6.1299. Min Act: -0.1700
Data Index: 6869558 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3799. Min Range: -6.3799
Max Act: 6.1299. Min Act: -0.1700
Data Index: 5163728 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3799. Min Range: -6.3799
Max Act: 6.1611. Min Act: -0.1700
Data Index: 1562652 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19