Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4916 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2090. Min Range: -8.2090
Max Act: 8.2090. Min Act: -0.1700
Data Index: 6350390 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2090. Min Range: -8.2090
Max Act: 8.1465. Min Act: -0.1700
Data Index: 6007499 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2090. Min Range: -8.2090
Max Act: 7.8965. Min Act: -0.1700
Data Index: 4259675 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2090. Min Range: -8.2090
Max Act: 7.5840. Min Act: -0.1700
Data Index: 4966944 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2090. Min Range: -8.2090
Max Act: 7.5215. Min Act: -0.1700
Data Index: 438068 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2090. Min Range: -8.2090
Max Act: 7.4590. Min Act: -0.1700
Data Index: 925463 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2090. Min Range: -8.2090
Max Act: 7.4590. Min Act: -0.1700
Data Index: 3035071 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2090. Min Range: -8.2090
Max Act: 7.4277. Min Act: -0.1700
Data Index: 5223360 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2090. Min Range: -8.2090
Max Act: 7.4277. Min Act: -0.1700
Data Index: 4104545 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2090. Min Range: -8.2090
Max Act: 7.3965. Min Act: -0.1700
Data Index: 2749351 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2090. Min Range: -8.2090
Max Act: 7.3652. Min Act: -0.1700
Data Index: 3062611 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2090. Min Range: -8.2090
Max Act: 7.3652. Min Act: -0.1700
Data Index: 181796 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2090. Min Range: -8.2090
Max Act: 7.3027. Min Act: -0.1700
Data Index: 7681947 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2090. Min Range: -8.2090
Max Act: 7.3340. Min Act: -0.1700
Data Index: 2459065 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2090. Min Range: -8.2090
Max Act: 7.3340. Min Act: -0.1700
Data Index: 8080021 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2090. Min Range: -8.2090
Max Act: 7.3340. Min Act: -0.1700
Data Index: 6132169 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2090. Min Range: -8.2090
Max Act: 7.3340. Min Act: -0.1700
Data Index: 1687095 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2090. Min Range: -8.2090
Max Act: 7.3027. Min Act: -0.1700
Data Index: 4407260 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2090. Min Range: -8.2090
Max Act: 7.2715. Min Act: -0.1700
Data Index: 7437870 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2090. Min Range: -8.2090
Max Act: 7.2715. Min Act: -0.1700
Data Index: 3809006 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19