Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2496 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5436. Min Range: -5.5436
Max Act: 5.5436. Min Act: -0.1700
Data Index: 2313390 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5436. Min Range: -5.5436
Max Act: 5.4499. Min Act: -0.1700
Data Index: 2886940 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5436. Min Range: -5.5436
Max Act: 5.4499. Min Act: -0.1700
Data Index: 7850179 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5436. Min Range: -5.5436
Max Act: 5.4499. Min Act: -0.1700
Data Index: 1791891 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5436. Min Range: -5.5436
Max Act: 5.3561. Min Act: -0.1700
Data Index: 1900778 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5436. Min Range: -5.5436
Max Act: 5.3561. Min Act: -0.1700
Data Index: 8069481 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5436. Min Range: -5.5436
Max Act: 5.3874. Min Act: -0.1700
Data Index: 264835 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5436. Min Range: -5.5436
Max Act: 5.3249. Min Act: -0.1700
Data Index: 6515618 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5436. Min Range: -5.5436
Max Act: 5.2936. Min Act: -0.1700
Data Index: 2397148 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5436. Min Range: -5.5436
Max Act: 5.3249. Min Act: -0.1700
Data Index: 445866 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5436. Min Range: -5.5436
Max Act: 5.2936. Min Act: -0.1700
Data Index: 6002907 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5436. Min Range: -5.5436
Max Act: 5.2624. Min Act: -0.1700
Data Index: 4518790 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5436. Min Range: -5.5436
Max Act: 5.2624. Min Act: -0.1700
Data Index: 31156 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5436. Min Range: -5.5436
Max Act: 5.2624. Min Act: -0.1700
Data Index: 1357668 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5436. Min Range: -5.5436
Max Act: 5.2311. Min Act: -0.1700
Data Index: 3478390 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5436. Min Range: -5.5436
Max Act: 5.2311. Min Act: -0.1700
Data Index: 7322730 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5436. Min Range: -5.5436
Max Act: 5.1999. Min Act: -0.1700
Data Index: 6571165 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5436. Min Range: -5.5436
Max Act: 5.2311. Min Act: -0.1700
Data Index: 781388 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5436. Min Range: -5.5436
Max Act: 5.1999. Min Act: -0.1700
Data Index: 2470715 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5436. Min Range: -5.5436
Max Act: 5.1999. Min Act: -0.1700
Data Index: 165579 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19