Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3535 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8771. Min Range: -4.8771
Max Act: 4.8771. Min Act: -0.1700
Data Index: 3336201 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8771. Min Range: -4.8771
Max Act: 4.7208. Min Act: -0.1700
Data Index: 3999625 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8771. Min Range: -4.8771
Max Act: 4.6271. Min Act: -0.1700
Data Index: 3453698 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8771. Min Range: -4.8771
Max Act: 4.6271. Min Act: -0.1700
Data Index: 1633206 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8771. Min Range: -4.8771
Max Act: 4.5958. Min Act: -0.1700
Data Index: 931271 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8771. Min Range: -4.8771
Max Act: 4.5646. Min Act: -0.1700
Data Index: 7195830 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8771. Min Range: -4.8771
Max Act: 4.5646. Min Act: -0.1700
Data Index: 4995504 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8771. Min Range: -4.8771
Max Act: 4.5021. Min Act: -0.1700
Data Index: 1548507 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8771. Min Range: -4.8771
Max Act: 4.5021. Min Act: -0.1700
Data Index: 7403970 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8771. Min Range: -4.8771
Max Act: 4.4708. Min Act: -0.1700
Data Index: 659824 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8771. Min Range: -4.8771
Max Act: 4.4396. Min Act: -0.1700
Data Index: 553768 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8771. Min Range: -4.8771
Max Act: 4.4083. Min Act: -0.1700
Data Index: 4314016 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8771. Min Range: -4.8771
Max Act: 4.3770. Min Act: -0.1700
Data Index: 2059727 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8771. Min Range: -4.8771
Max Act: 4.3770. Min Act: -0.1700
Data Index: 6077156 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8771. Min Range: -4.8771
Max Act: 4.3458. Min Act: -0.1700
Data Index: 4195773 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8771. Min Range: -4.8771
Max Act: 4.3458. Min Act: -0.1700
Data Index: 1598955 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8771. Min Range: -4.8771
Max Act: 4.2833. Min Act: -0.1700
Data Index: 2618296 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8771. Min Range: -4.8771
Max Act: 4.2833. Min Act: -0.1700
Data Index: 1292073 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8771. Min Range: -4.8771
Max Act: 4.2833. Min Act: -0.1700
Data Index: 6061075 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8771. Min Range: -4.8771
Max Act: 4.2520. Min Act: -0.1700
Data Index: 758364 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19