Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 362 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5000. Min Range: -6.5000
Max Act: 6.5000. Min Act: -0.1700
Data Index: 3079368 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5000. Min Range: -6.5000
Max Act: 6.0000. Min Act: -0.1700
Data Index: 2233101 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5000. Min Range: -6.5000
Max Act: 5.9688. Min Act: -0.1700
Data Index: 5360089 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5000. Min Range: -6.5000
Max Act: 5.9688. Min Act: -0.1700
Data Index: 4928557 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5000. Min Range: -6.5000
Max Act: 5.9688. Min Act: -0.1700
Data Index: 8127434 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5000. Min Range: -6.5000
Max Act: 5.9375. Min Act: -0.1700
Data Index: 6653438 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5000. Min Range: -6.5000
Max Act: 5.9375. Min Act: -0.1700
Data Index: 449452 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5000. Min Range: -6.5000
Max Act: 5.9063. Min Act: -0.1700
Data Index: 6040181 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5000. Min Range: -6.5000
Max Act: 5.9063. Min Act: -0.1700
Data Index: 369770 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5000. Min Range: -6.5000
Max Act: 5.8750. Min Act: -0.1700
Data Index: 2358298 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5000. Min Range: -6.5000
Max Act: 5.9063. Min Act: -0.1700
Data Index: 6304990 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5000. Min Range: -6.5000
Max Act: 5.9063. Min Act: -0.1700
Data Index: 7981979 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5000. Min Range: -6.5000
Max Act: 5.9063. Min Act: -0.1700
Data Index: 736732 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5000. Min Range: -6.5000
Max Act: 5.9063. Min Act: -0.1700
Data Index: 61307 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5000. Min Range: -6.5000
Max Act: 5.8750. Min Act: -0.1700
Data Index: 249409 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5000. Min Range: -6.5000
Max Act: 5.8750. Min Act: -0.1700
Data Index: 2324183 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5000. Min Range: -6.5000
Max Act: 5.8750. Min Act: -0.1700
Data Index: 16968 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5000. Min Range: -6.5000
Max Act: 5.8125. Min Act: -0.1700
Data Index: 5928920 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5000. Min Range: -6.5000
Max Act: 5.8438. Min Act: -0.1700
Data Index: 8117007 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5000. Min Range: -6.5000
Max Act: 5.8438. Min Act: -0.1700
Data Index: 7696498 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19