Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1002 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8899. Min Range: -5.8899
Max Act: 5.8586. Min Act: -0.1700
Data Index: 2879465 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8899. Min Range: -5.8899
Max Act: 5.8899. Min Act: -0.1700
Data Index: 846389 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8899. Min Range: -5.8899
Max Act: 5.8274. Min Act: -0.1700
Data Index: 4172917 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8899. Min Range: -5.8899
Max Act: 5.7649. Min Act: -0.1700
Data Index: 5391651 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8899. Min Range: -5.8899
Max Act: 5.7024. Min Act: -0.1700
Data Index: 526781 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8899. Min Range: -5.8899
Max Act: 5.6399. Min Act: -0.1700
Data Index: 6265396 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8899. Min Range: -5.8899
Max Act: 5.6399. Min Act: -0.1700
Data Index: 3793544 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8899. Min Range: -5.8899
Max Act: 5.6711. Min Act: -0.1700
Data Index: 7527361 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8899. Min Range: -5.8899
Max Act: 5.5774. Min Act: -0.1700
Data Index: 390665 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8899. Min Range: -5.8899
Max Act: 5.6399. Min Act: -0.1700
Data Index: 496182 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8899. Min Range: -5.8899
Max Act: 5.5461. Min Act: -0.1700
Data Index: 5479930 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8899. Min Range: -5.8899
Max Act: 5.5149. Min Act: -0.1700
Data Index: 7209249 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8899. Min Range: -5.8899
Max Act: 5.5149. Min Act: -0.1700
Data Index: 2836805 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8899. Min Range: -5.8899
Max Act: 5.5149. Min Act: -0.1700
Data Index: 533078 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8899. Min Range: -5.8899
Max Act: 5.5149. Min Act: -0.1700
Data Index: 2042248 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8899. Min Range: -5.8899
Max Act: 5.5149. Min Act: -0.1700
Data Index: 18036 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8899. Min Range: -5.8899
Max Act: 5.5149. Min Act: -0.1700
Data Index: 6997694 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8899. Min Range: -5.8899
Max Act: 5.4524. Min Act: -0.1700
Data Index: 2011 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8899. Min Range: -5.8899
Max Act: 5.4211. Min Act: -0.1700
Data Index: 2904705 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8899. Min Range: -5.8899
Max Act: 5.4524. Min Act: -0.1700
Data Index: 677375 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19