Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4172 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6483. Min Range: -4.6483
Max Act: 4.6483. Min Act: -0.1700
Data Index: 6013669 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6483. Min Range: -4.6483
Max Act: 4.5546. Min Act: -0.1700
Data Index: 7150260 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6483. Min Range: -4.6483
Max Act: 4.5233. Min Act: -0.1700
Data Index: 1962045 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6483. Min Range: -4.6483
Max Act: 4.5233. Min Act: -0.1700
Data Index: 8337707 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6483. Min Range: -4.6483
Max Act: 4.5233. Min Act: -0.1700
Data Index: 4141824 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6483. Min Range: -4.6483
Max Act: 4.4921. Min Act: -0.1700
Data Index: 2826855 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6483. Min Range: -4.6483
Max Act: 4.4921. Min Act: -0.1700
Data Index: 1453170 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6483. Min Range: -4.6483
Max Act: 4.4608. Min Act: -0.1700
Data Index: 7405985 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6483. Min Range: -4.6483
Max Act: 4.4608. Min Act: -0.1700
Data Index: 1403202 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6483. Min Range: -4.6483
Max Act: 4.4608. Min Act: -0.1700
Data Index: 2336972 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6483. Min Range: -4.6483
Max Act: 4.4296. Min Act: -0.1700
Data Index: 5469583 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6483. Min Range: -4.6483
Max Act: 4.3671. Min Act: -0.1700
Data Index: 3578177 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6483. Min Range: -4.6483
Max Act: 4.3358. Min Act: -0.1700
Data Index: 6855057 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6483. Min Range: -4.6483
Max Act: 4.3358. Min Act: -0.1700
Data Index: 5747548 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6483. Min Range: -4.6483
Max Act: 4.3671. Min Act: -0.1700
Data Index: 274293 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6483. Min Range: -4.6483
Max Act: 4.3983. Min Act: -0.1700
Data Index: 8492796 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6483. Min Range: -4.6483
Max Act: 4.3671. Min Act: -0.1700
Data Index: 2927589 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6483. Min Range: -4.6483
Max Act: 4.3358. Min Act: -0.1700
Data Index: 3543919 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6483. Min Range: -4.6483
Max Act: 4.3358. Min Act: -0.1700
Data Index: 5181880 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6483. Min Range: -4.6483
Max Act: 4.3358. Min Act: -0.1700
Data Index: 8424376 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19