Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3711 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2394. Min Range: -5.2394
Max Act: 5.2394. Min Act: -0.1700
Data Index: 4222011 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.8019. Min Act: -0.1700
Data Index: 8827308 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.7394. Min Act: -0.1700
Data Index: 822978 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.7394. Min Act: -0.1700
Data Index: 7914363 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.7394. Min Act: -0.1700
Data Index: 5914674 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.7081. Min Act: -0.1700
Data Index: 2040684 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.6769. Min Act: -0.1700
Data Index: 1937583 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.6769. Min Act: -0.1700
Data Index: 7885440 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.7081. Min Act: -0.1700
Data Index: 2835081 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.6456. Min Act: -0.1700
Data Index: 96222 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.6456. Min Act: -0.1700
Data Index: 7564917 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.6456. Min Act: -0.1700
Data Index: 3526579 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.6144. Min Act: -0.1700
Data Index: 4707562 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.6144. Min Act: -0.1700
Data Index: 5961684 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.6144. Min Act: -0.1700
Data Index: 4707567 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.6144. Min Act: -0.1700
Data Index: 6041005 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.5831. Min Act: -0.1700
Data Index: 3913253 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.5831. Min Act: -0.1700
Data Index: 5752898 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.6144. Min Act: -0.1700
Data Index: 669362 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.5831. Min Act: -0.1700
Data Index: 3950143 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19