Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6230 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8655. Min Range: -5.8655
Max Act: 5.8655. Min Act: -0.1700
Data Index: 2095481 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8655. Min Range: -5.8655
Max Act: 5.8342. Min Act: -0.1700
Data Index: 6449176 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8655. Min Range: -5.8655
Max Act: 5.7405. Min Act: -0.1700
Data Index: 7051026 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8655. Min Range: -5.8655
Max Act: 5.6467. Min Act: -0.1700
Data Index: 2588474 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8655. Min Range: -5.8655
Max Act: 5.6155. Min Act: -0.1700
Data Index: 2842544 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8655. Min Range: -5.8655
Max Act: 5.6155. Min Act: -0.1700
Data Index: 2550919 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8655. Min Range: -5.8655
Max Act: 5.5530. Min Act: -0.1700
Data Index: 2868336 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8655. Min Range: -5.8655
Max Act: 5.5530. Min Act: -0.1700
Data Index: 6535969 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8655. Min Range: -5.8655
Max Act: 5.5530. Min Act: -0.1700
Data Index: 7477211 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8655. Min Range: -5.8655
Max Act: 5.5217. Min Act: -0.1700
Data Index: 7946322 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8655. Min Range: -5.8655
Max Act: 5.5217. Min Act: -0.1700
Data Index: 6996892 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8655. Min Range: -5.8655
Max Act: 5.5530. Min Act: -0.1700
Data Index: 6688385 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8655. Min Range: -5.8655
Max Act: 5.4592. Min Act: -0.1700
Data Index: 4420735 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8655. Min Range: -5.8655
Max Act: 5.4592. Min Act: -0.1700
Data Index: 8399980 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8655. Min Range: -5.8655
Max Act: 5.4280. Min Act: -0.1700
Data Index: 1760414 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8655. Min Range: -5.8655
Max Act: 5.3967. Min Act: -0.1700
Data Index: 6084938 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8655. Min Range: -5.8655
Max Act: 5.4280. Min Act: -0.1700
Data Index: 8684138 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8655. Min Range: -5.8655
Max Act: 5.4280. Min Act: -0.1700
Data Index: 5886503 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8655. Min Range: -5.8655
Max Act: 5.4280. Min Act: -0.1700
Data Index: 7733857 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8655. Min Range: -5.8655
Max Act: 5.3967. Min Act: -0.1700
Data Index: 7895103 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19