Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2047 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6444. Min Range: -7.6444
Max Act: 7.6444. Min Act: -0.1700
Data Index: 4558992 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6444. Min Range: -7.6444
Max Act: 7.5819. Min Act: -0.1700
Data Index: 4656321 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6444. Min Range: -7.6444
Max Act: 7.5194. Min Act: -0.1700
Data Index: 8352540 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6444. Min Range: -7.6444
Max Act: 7.5194. Min Act: -0.1700
Data Index: 3515627 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6444. Min Range: -7.6444
Max Act: 7.4881. Min Act: -0.1700
Data Index: 6150022 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6444. Min Range: -7.6444
Max Act: 7.4256. Min Act: -0.1700
Data Index: 2149482 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6444. Min Range: -7.6444
Max Act: 7.3319. Min Act: -0.1700
Data Index: 8044526 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6444. Min Range: -7.6444
Max Act: 7.3319. Min Act: -0.1700
Data Index: 5239822 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6444. Min Range: -7.6444
Max Act: 7.2694. Min Act: -0.1700
Data Index: 96558 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6444. Min Range: -7.6444
Max Act: 7.2694. Min Act: -0.1700
Data Index: 3915126 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6444. Min Range: -7.6444
Max Act: 7.2381. Min Act: -0.1700
Data Index: 4799450 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6444. Min Range: -7.6444
Max Act: 7.1756. Min Act: -0.1700
Data Index: 3531329 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6444. Min Range: -7.6444
Max Act: 7.2069. Min Act: -0.1700
Data Index: 2513379 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6444. Min Range: -7.6444
Max Act: 7.1444. Min Act: -0.1700
Data Index: 4123695 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6444. Min Range: -7.6444
Max Act: 7.1444. Min Act: -0.1700
Data Index: 630267 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6444. Min Range: -7.6444
Max Act: 7.1131. Min Act: -0.1700
Data Index: 814181 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6444. Min Range: -7.6444
Max Act: 7.1131. Min Act: -0.1700
Data Index: 8627515 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6444. Min Range: -7.6444
Max Act: 7.0819. Min Act: -0.1700
Data Index: 3809975 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6444. Min Range: -7.6444
Max Act: 7.0194. Min Act: -0.1700
Data Index: 5790344 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6444. Min Range: -7.6444
Max Act: 7.0194. Min Act: -0.1700
Data Index: 546249 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19