Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4910 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8428. Min Range: -6.8428
Max Act: 6.8428. Min Act: -0.1700
Data Index: 6801664 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8428. Min Range: -6.8428
Max Act: 6.7491. Min Act: -0.1699
Data Index: 4938548 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8428. Min Range: -6.8428
Max Act: 6.6553. Min Act: -0.1700
Data Index: 867708 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8428. Min Range: -6.8428
Max Act: 6.6553. Min Act: -0.1700
Data Index: 8543930 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8428. Min Range: -6.8428
Max Act: 6.5928. Min Act: -0.1700
Data Index: 7492997 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8428. Min Range: -6.8428
Max Act: 6.5616. Min Act: -0.1700
Data Index: 6833665 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8428. Min Range: -6.8428
Max Act: 6.5303. Min Act: -0.1700
Data Index: 8110488 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8428. Min Range: -6.8428
Max Act: 6.4366. Min Act: -0.1700
Data Index: 7150291 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8428. Min Range: -6.8428
Max Act: 6.4366. Min Act: -0.1700
Data Index: 7087497 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8428. Min Range: -6.8428
Max Act: 6.4053. Min Act: -0.1700
Data Index: 6628838 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8428. Min Range: -6.8428
Max Act: 6.3428. Min Act: -0.1700
Data Index: 8077083 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8428. Min Range: -6.8428
Max Act: 6.3741. Min Act: -0.1700
Data Index: 4551011 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8428. Min Range: -6.8428
Max Act: 6.3428. Min Act: -0.1700
Data Index: 5738730 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8428. Min Range: -6.8428
Max Act: 6.3741. Min Act: -0.1700
Data Index: 361652 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8428. Min Range: -6.8428
Max Act: 6.3428. Min Act: -0.1700
Data Index: 1448935 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8428. Min Range: -6.8428
Max Act: 6.3428. Min Act: -0.1700
Data Index: 399093 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8428. Min Range: -6.8428
Max Act: 6.3116. Min Act: -0.1700
Data Index: 184107 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8428. Min Range: -6.8428
Max Act: 6.2803. Min Act: -0.1700
Data Index: 7052223 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8428. Min Range: -6.8428
Max Act: 6.3116. Min Act: -0.1700
Data Index: 6589922 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8428. Min Range: -6.8428
Max Act: 6.2491. Min Act: -0.1700
Data Index: 5215297 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19