Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4832 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1521. Min Range: -5.1521
Max Act: 5.1521. Min Act: -0.1700
Data Index: 4401945 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1521. Min Range: -5.1521
Max Act: 5.0271. Min Act: -0.1700
Data Index: 7489215 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1521. Min Range: -5.1521
Max Act: 5.0271. Min Act: -0.1700
Data Index: 5402638 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1521. Min Range: -5.1521
Max Act: 5.0271. Min Act: -0.1700
Data Index: 8467334 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1521. Min Range: -5.1521
Max Act: 4.9646. Min Act: -0.1700
Data Index: 4609770 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1521. Min Range: -5.1521
Max Act: 4.9334. Min Act: -0.1700
Data Index: 3024600 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1521. Min Range: -5.1521
Max Act: 4.9021. Min Act: -0.1700
Data Index: 1140324 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1521. Min Range: -5.1521
Max Act: 4.9334. Min Act: -0.1700
Data Index: 4300380 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1521. Min Range: -5.1521
Max Act: 4.9021. Min Act: -0.1700
Data Index: 5234596 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1521. Min Range: -5.1521
Max Act: 4.8396. Min Act: -0.1700
Data Index: 244023 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1521. Min Range: -5.1521
Max Act: 4.8709. Min Act: -0.1700
Data Index: 7040650 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1521. Min Range: -5.1521
Max Act: 4.8396. Min Act: -0.1700
Data Index: 8713490 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1521. Min Range: -5.1521
Max Act: 4.8084. Min Act: -0.1700
Data Index: 5567928 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1521. Min Range: -5.1521
Max Act: 4.8084. Min Act: -0.1700
Data Index: 970443 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1521. Min Range: -5.1521
Max Act: 4.7771. Min Act: -0.1700
Data Index: 4346460 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1521. Min Range: -5.1521
Max Act: 4.7771. Min Act: -0.1700
Data Index: 3865603 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1521. Min Range: -5.1521
Max Act: 4.7771. Min Act: -0.1700
Data Index: 7991062 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1521. Min Range: -5.1521
Max Act: 4.7771. Min Act: -0.1700
Data Index: 23482 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1521. Min Range: -5.1521
Max Act: 4.7771. Min Act: -0.1700
Data Index: 3559456 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1521. Min Range: -5.1521
Max Act: 4.7459. Min Act: -0.1700
Data Index: 4842935 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19