Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3419 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.6927. Min Range: -0.6927
Max Act: 0.6927. Min Act: -0.1700
Data Index: 7079402 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6927. Min Range: -0.6927
Max Act: 0.6927. Min Act: -0.1700
Data Index: 6898375 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6927. Min Range: -0.6927
Max Act: 0.6846. Min Act: -0.1700
Data Index: 7834215 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6927. Min Range: -0.6927
Max Act: 0.6684. Min Act: -0.1694
Data Index: 8208248 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6927. Min Range: -0.6927
Max Act: 0.6765. Min Act: -0.1700
Data Index: 5259208 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6927. Min Range: -0.6927
Max Act: 0.6523. Min Act: -0.1700
Data Index: 7919792 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6927. Min Range: -0.6927
Max Act: 0.6363. Min Act: -0.1679
Data Index: 1063243 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6927. Min Range: -0.6927
Max Act: 0.6283. Min Act: -0.1700
Data Index: 3564393 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6927. Min Range: -0.6927
Max Act: 0.6443. Min Act: -0.1700
Data Index: 7647171 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6927. Min Range: -0.6927
Max Act: 0.6283. Min Act: -0.1700
Data Index: 4127599 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6927. Min Range: -0.6927
Max Act: 0.6283. Min Act: -0.1696
Data Index: 2039767 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6927. Min Range: -0.6927
Max Act: 0.6204. Min Act: -0.1700
Data Index: 4853449 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6927. Min Range: -0.6927
Max Act: 0.6283. Min Act: -0.1694
Data Index: 7934332 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6927. Min Range: -0.6927
Max Act: 0.6283. Min Act: -0.1699
Data Index: 6670531 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6927. Min Range: -0.6927
Max Act: 0.6125. Min Act: -0.1698
Data Index: 3124108 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6927. Min Range: -0.6927
Max Act: 0.6204. Min Act: -0.1700
Data Index: 5658217 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6927. Min Range: -0.6927
Max Act: 0.6125. Min Act: -0.1661
Data Index: 5225146 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6927. Min Range: -0.6927
Max Act: 0.6125. Min Act: -0.1699
Data Index: 6133636 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6927. Min Range: -0.6927
Max Act: 0.6046. Min Act: -0.1696
Data Index: 6019544 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6927. Min Range: -0.6927
Max Act: 0.5888. Min Act: -0.1700
Data Index: 5542900 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19