Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2342 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2380. Min Range: -3.2380
Max Act: 3.2380. Min Act: -0.1700
Data Index: 5092174 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2380. Min Range: -3.2380
Max Act: 3.1751. Min Act: -0.1700
Data Index: 4801434 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2380. Min Range: -3.2380
Max Act: 3.1751. Min Act: -0.1700
Data Index: 22989 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2380. Min Range: -3.2380
Max Act: 3.1594. Min Act: -0.1700
Data Index: 2116690 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2380. Min Range: -3.2380
Max Act: 3.1437. Min Act: -0.1700
Data Index: 4489386 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2380. Min Range: -3.2380
Max Act: 3.1437. Min Act: -0.1700
Data Index: 7751960 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2380. Min Range: -3.2380
Max Act: 3.1122. Min Act: -0.1700
Data Index: 3701209 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2380. Min Range: -3.2380
Max Act: 3.1594. Min Act: -0.1700
Data Index: 8498097 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2380. Min Range: -3.2380
Max Act: 3.1279. Min Act: -0.1700
Data Index: 19602 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2380. Min Range: -3.2380
Max Act: 3.1279. Min Act: -0.1700
Data Index: 369324 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2380. Min Range: -3.2380
Max Act: 3.1122. Min Act: -0.1700
Data Index: 2073742 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2380. Min Range: -3.2380
Max Act: 3.1437. Min Act: -0.1700
Data Index: 775516 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2380. Min Range: -3.2380
Max Act: 3.1122. Min Act: -0.1700
Data Index: 4574164 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2380. Min Range: -3.2380
Max Act: 3.1122. Min Act: -0.1700
Data Index: 7887714 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2380. Min Range: -3.2380
Max Act: 3.1279. Min Act: -0.1700
Data Index: 3757278 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2380. Min Range: -3.2380
Max Act: 3.0964. Min Act: -0.1700
Data Index: 6373319 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2380. Min Range: -3.2380
Max Act: 3.1122. Min Act: -0.1700
Data Index: 3973487 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2380. Min Range: -3.2380
Max Act: 3.1279. Min Act: -0.1700
Data Index: 6766419 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2380. Min Range: -3.2380
Max Act: 3.1122. Min Act: -0.1700
Data Index: 4087859 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2380. Min Range: -3.2380
Max Act: 3.1122. Min Act: -0.1700
Data Index: 5724818 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19