Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3521 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5086. Min Range: -6.5086
Max Act: 6.5086. Min Act: -0.1700
Data Index: 1787522 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5086. Min Range: -6.5086
Max Act: 6.4148. Min Act: -0.1700
Data Index: 1228893 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5086. Min Range: -6.5086
Max Act: 6.3523. Min Act: -0.1700
Data Index: 152317 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5086. Min Range: -6.5086
Max Act: 6.3523. Min Act: -0.1700
Data Index: 2309369 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5086. Min Range: -6.5086
Max Act: 6.2898. Min Act: -0.1700
Data Index: 5901822 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5086. Min Range: -6.5086
Max Act: 6.2898. Min Act: -0.1700
Data Index: 4855129 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5086. Min Range: -6.5086
Max Act: 6.2273. Min Act: -0.1700
Data Index: 215583 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5086. Min Range: -6.5086
Max Act: 6.1961. Min Act: -0.1700
Data Index: 78038 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5086. Min Range: -6.5086
Max Act: 6.1648. Min Act: -0.1700
Data Index: 8476786 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5086. Min Range: -6.5086
Max Act: 6.1648. Min Act: -0.1700
Data Index: 5635758 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5086. Min Range: -6.5086
Max Act: 6.1336. Min Act: -0.1700
Data Index: 5254521 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5086. Min Range: -6.5086
Max Act: 6.1648. Min Act: -0.1700
Data Index: 5792081 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5086. Min Range: -6.5086
Max Act: 6.1023. Min Act: -0.1700
Data Index: 8810272 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5086. Min Range: -6.5086
Max Act: 6.0398. Min Act: -0.1700
Data Index: 7845970 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5086. Min Range: -6.5086
Max Act: 6.0398. Min Act: -0.1700
Data Index: 3266958 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5086. Min Range: -6.5086
Max Act: 6.0711. Min Act: -0.1700
Data Index: 8375129 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5086. Min Range: -6.5086
Max Act: 6.0398. Min Act: -0.1700
Data Index: 5585518 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5086. Min Range: -6.5086
Max Act: 6.0398. Min Act: -0.1700
Data Index: 4344455 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5086. Min Range: -6.5086
Max Act: 6.0398. Min Act: -0.1700
Data Index: 1898806 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5086. Min Range: -6.5086
Max Act: 6.0086. Min Act: -0.1700
Data Index: 3246902 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19