Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3089 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.6352. Min Act: -0.1700
Data Index: 4892784 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.5414. Min Act: -0.1700
Data Index: 6346312 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.5414. Min Act: -0.1700
Data Index: 4078693 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.4477. Min Act: -0.1700
Data Index: 3014002 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.4477. Min Act: -0.1700
Data Index: 3324856 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.4477. Min Act: -0.1700
Data Index: 5967625 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.3539. Min Act: -0.1700
Data Index: 3048363 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.3539. Min Act: -0.1700
Data Index: 5415619 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.3852. Min Act: -0.1700
Data Index: 1964337 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.3539. Min Act: -0.1700
Data Index: 2750746 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.3227. Min Act: -0.1700
Data Index: 1784431 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.3227. Min Act: -0.1700
Data Index: 6624016 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.3227. Min Act: -0.1700
Data Index: 4087904 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.3227. Min Act: -0.1700
Data Index: 8408785 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.3227. Min Act: -0.1700
Data Index: 2434286 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.3227. Min Act: -0.1700
Data Index: 3436300 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.2914. Min Act: -0.1700
Data Index: 3519203 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.3227. Min Act: -0.1700
Data Index: 5323051 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.2914. Min Act: -0.1700
Data Index: 3109807 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6352. Min Range: -4.6352
Max Act: 4.2602. Min Act: -0.1700
Data Index: 657640 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19