Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2859 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4513. Min Range: -5.4513
Max Act: 5.4513. Min Act: -0.1700
Data Index: 5434564 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4513. Min Range: -5.4513
Max Act: 5.3888. Min Act: -0.1700
Data Index: 4940488 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4513. Min Range: -5.4513
Max Act: 5.3575. Min Act: -0.1700
Data Index: 4940489 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4513. Min Range: -5.4513
Max Act: 5.3263. Min Act: -0.1700
Data Index: 6299720 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4513. Min Range: -5.4513
Max Act: 5.2638. Min Act: -0.1700
Data Index: 1748257 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4513. Min Range: -5.4513
Max Act: 5.2950. Min Act: -0.1700
Data Index: 4981740 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4513. Min Range: -5.4513
Max Act: 5.2638. Min Act: -0.1700
Data Index: 1263034 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4513. Min Range: -5.4513
Max Act: 5.2638. Min Act: -0.1700
Data Index: 5582437 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4513. Min Range: -5.4513
Max Act: 5.2950. Min Act: -0.1700
Data Index: 1165466 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4513. Min Range: -5.4513
Max Act: 5.2638. Min Act: -0.1700
Data Index: 6706419 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4513. Min Range: -5.4513
Max Act: 5.2325. Min Act: -0.1700
Data Index: 628769 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4513. Min Range: -5.4513
Max Act: 5.2638. Min Act: -0.1700
Data Index: 934747 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4513. Min Range: -5.4513
Max Act: 5.2325. Min Act: -0.1700
Data Index: 1263036 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4513. Min Range: -5.4513
Max Act: 5.2325. Min Act: -0.1700
Data Index: 8491489 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4513. Min Range: -5.4513
Max Act: 5.2325. Min Act: -0.1700
Data Index: 8220428 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4513. Min Range: -5.4513
Max Act: 5.2325. Min Act: -0.1700
Data Index: 6081755 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4513. Min Range: -5.4513
Max Act: 5.2325. Min Act: -0.1700
Data Index: 4003508 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4513. Min Range: -5.4513
Max Act: 5.2638. Min Act: -0.1700
Data Index: 6483879 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4513. Min Range: -5.4513
Max Act: 5.2013. Min Act: -0.1700
Data Index: 5114599 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4513. Min Range: -5.4513
Max Act: 5.2013. Min Act: -0.1700
Data Index: 5272686 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19