Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1778 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3585. Min Range: -7.3585
Max Act: 7.3585. Min Act: -0.1700
Data Index: 3573213 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3585. Min Range: -7.3585
Max Act: 7.3273. Min Act: -0.1700
Data Index: 7089017 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3585. Min Range: -7.3585
Max Act: 7.2335. Min Act: -0.1700
Data Index: 5937516 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3585. Min Range: -7.3585
Max Act: 7.2023. Min Act: -0.1700
Data Index: 2736532 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3585. Min Range: -7.3585
Max Act: 7.1710. Min Act: -0.1700
Data Index: 689418 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3585. Min Range: -7.3585
Max Act: 7.1398. Min Act: -0.1700
Data Index: 4259278 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3585. Min Range: -7.3585
Max Act: 7.0773. Min Act: -0.1700
Data Index: 7184044 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3585. Min Range: -7.3585
Max Act: 7.0773. Min Act: -0.1700
Data Index: 737270 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3585. Min Range: -7.3585
Max Act: 7.0460. Min Act: -0.1700
Data Index: 5823658 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3585. Min Range: -7.3585
Max Act: 7.0148. Min Act: -0.1700
Data Index: 7173907 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3585. Min Range: -7.3585
Max Act: 6.9523. Min Act: -0.1700
Data Index: 1583848 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3585. Min Range: -7.3585
Max Act: 6.9523. Min Act: -0.1700
Data Index: 8104407 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3585. Min Range: -7.3585
Max Act: 6.9523. Min Act: -0.1700
Data Index: 6660184 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3585. Min Range: -7.3585
Max Act: 6.9210. Min Act: -0.1700
Data Index: 4801573 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3585. Min Range: -7.3585
Max Act: 6.8898. Min Act: -0.1700
Data Index: 5823657 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3585. Min Range: -7.3585
Max Act: 6.8273. Min Act: -0.1700
Data Index: 100451 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3585. Min Range: -7.3585
Max Act: 6.7960. Min Act: -0.1700
Data Index: 2434976 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3585. Min Range: -7.3585
Max Act: 6.8273. Min Act: -0.1700
Data Index: 8603331 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3585. Min Range: -7.3585
Max Act: 6.8585. Min Act: -0.1700
Data Index: 5454902 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3585. Min Range: -7.3585
Max Act: 6.8273. Min Act: -0.1700
Data Index: 747732 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19