Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3645 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3323. Min Range: -7.3323
Max Act: 7.3323. Min Act: 0.3445
Data Index: 840567 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3323. Min Range: -7.3323
Max Act: 7.2385. Min Act: 0.4448
Data Index: 4854406 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3323. Min Range: -7.3323
Max Act: 7.2385. Min Act: 0.9785
Data Index: 8567513 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3323. Min Range: -7.3323
Max Act: 7.2698. Min Act: 1.1619
Data Index: 7546427 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3323. Min Range: -7.3323
Max Act: 7.2073. Min Act: 0.2288
Data Index: 4526665 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3323. Min Range: -7.3323
Max Act: 7.2385. Min Act: 0.1259
Data Index: 3345198 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3323. Min Range: -7.3323
Max Act: 7.1760. Min Act: 0.6575
Data Index: 3706967 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3323. Min Range: -7.3323
Max Act: 7.1760. Min Act: -0.0966
Data Index: 2325448 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3323. Min Range: -7.3323
Max Act: 7.1760. Min Act: 0.0141
Data Index: 8396132 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3323. Min Range: -7.3323
Max Act: 7.1760. Min Act: 0.2761
Data Index: 6650127 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3323. Min Range: -7.3323
Max Act: 7.1760. Min Act: 0.3254
Data Index: 7772758 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3323. Min Range: -7.3323
Max Act: 7.1760. Min Act: 0.2456
Data Index: 6718236 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3323. Min Range: -7.3323
Max Act: 7.1448. Min Act: 0.2666
Data Index: 3951982 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3323. Min Range: -7.3323
Max Act: 7.1448. Min Act: 0.1804
Data Index: 4174344 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3323. Min Range: -7.3323
Max Act: 7.1448. Min Act: 0.4321
Data Index: 6325790 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3323. Min Range: -7.3323
Max Act: 7.1760. Min Act: 0.3072
Data Index: 8629003 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3323. Min Range: -7.3323
Max Act: 7.1760. Min Act: 0.1650
Data Index: 4453355 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3323. Min Range: -7.3323
Max Act: 7.1448. Min Act: 0.1581
Data Index: 4858422 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3323. Min Range: -7.3323
Max Act: 7.1448. Min Act: 0.0539
Data Index: 2407573 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3323. Min Range: -7.3323
Max Act: 7.1448. Min Act: 0.3638
Data Index: 8792153 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19