Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6084 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2405. Min Range: -6.2405
Max Act: 6.2405. Min Act: -0.1700
Data Index: 3077882 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2405. Min Range: -6.2405
Max Act: 6.1155. Min Act: -0.1700
Data Index: 6726715 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2405. Min Range: -6.2405
Max Act: 6.0530. Min Act: -0.1700
Data Index: 6833286 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2405. Min Range: -6.2405
Max Act: 5.9905. Min Act: -0.1700
Data Index: 2300462 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2405. Min Range: -6.2405
Max Act: 5.9905. Min Act: -0.1700
Data Index: 1038999 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2405. Min Range: -6.2405
Max Act: 5.9592. Min Act: -0.1700
Data Index: 6503967 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2405. Min Range: -6.2405
Max Act: 5.9592. Min Act: -0.1700
Data Index: 220664 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2405. Min Range: -6.2405
Max Act: 5.9592. Min Act: -0.1700
Data Index: 2926708 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2405. Min Range: -6.2405
Max Act: 5.9280. Min Act: -0.1700
Data Index: 4046663 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2405. Min Range: -6.2405
Max Act: 5.9280. Min Act: -0.1700
Data Index: 5068071 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2405. Min Range: -6.2405
Max Act: 5.8967. Min Act: -0.1700
Data Index: 7752365 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2405. Min Range: -6.2405
Max Act: 5.8967. Min Act: -0.1700
Data Index: 1450062 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2405. Min Range: -6.2405
Max Act: 5.8655. Min Act: -0.1700
Data Index: 3569251 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2405. Min Range: -6.2405
Max Act: 5.8655. Min Act: -0.1700
Data Index: 305692 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2405. Min Range: -6.2405
Max Act: 5.8655. Min Act: -0.1700
Data Index: 5116892 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2405. Min Range: -6.2405
Max Act: 5.8342. Min Act: -0.1700
Data Index: 210199 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2405. Min Range: -6.2405
Max Act: 5.8342. Min Act: -0.1700
Data Index: 4254456 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2405. Min Range: -6.2405
Max Act: 5.8030. Min Act: -0.1700
Data Index: 2970933 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2405. Min Range: -6.2405
Max Act: 5.8342. Min Act: -0.1700
Data Index: 6047164 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2405. Min Range: -6.2405
Max Act: 5.8342. Min Act: -0.1700
Data Index: 5076379 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19