Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3650 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5327. Min Range: -6.5327
Max Act: 6.5327. Min Act: -0.1700
Data Index: 5193359 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5327. Min Range: -6.5327
Max Act: 6.2827. Min Act: -0.1700
Data Index: 2489492 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5327. Min Range: -6.5327
Max Act: 6.2827. Min Act: -0.1700
Data Index: 4742917 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5327. Min Range: -6.5327
Max Act: 6.2514. Min Act: -0.1700
Data Index: 666238 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5327. Min Range: -6.5327
Max Act: 6.2202. Min Act: -0.1700
Data Index: 5785165 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5327. Min Range: -6.5327
Max Act: 6.2202. Min Act: -0.1700
Data Index: 3349937 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5327. Min Range: -6.5327
Max Act: 6.1889. Min Act: -0.1700
Data Index: 646453 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5327. Min Range: -6.5327
Max Act: 6.1577. Min Act: -0.1700
Data Index: 5391169 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5327. Min Range: -6.5327
Max Act: 6.1264. Min Act: -0.1700
Data Index: 4484814 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5327. Min Range: -6.5327
Max Act: 6.1889. Min Act: -0.1700
Data Index: 325875 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5327. Min Range: -6.5327
Max Act: 6.1577. Min Act: -0.1700
Data Index: 7760409 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5327. Min Range: -6.5327
Max Act: 6.1264. Min Act: -0.1700
Data Index: 7114939 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5327. Min Range: -6.5327
Max Act: 6.0952. Min Act: -0.1700
Data Index: 7448570 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5327. Min Range: -6.5327
Max Act: 6.0952. Min Act: -0.1700
Data Index: 7727441 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5327. Min Range: -6.5327
Max Act: 6.0952. Min Act: -0.1700
Data Index: 5561247 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5327. Min Range: -6.5327
Max Act: 6.0639. Min Act: -0.1700
Data Index: 5995836 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5327. Min Range: -6.5327
Max Act: 6.0639. Min Act: -0.1700
Data Index: 6642346 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5327. Min Range: -6.5327
Max Act: 6.0639. Min Act: -0.1700
Data Index: 3334297 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5327. Min Range: -6.5327
Max Act: 6.0327. Min Act: -0.1700
Data Index: 3054877 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5327. Min Range: -6.5327
Max Act: 6.0327. Min Act: -0.1700
Data Index: 597844 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19