Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3498. Min Range: -9.3498
Max Act: 9.3498. Min Act: -0.1700
Data Index: 3430751 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3498. Min Range: -9.3498
Max Act: 9.1623. Min Act: -0.1700
Data Index: 7397245 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3498. Min Range: -9.3498
Max Act: 9.1623. Min Act: -0.1700
Data Index: 170096 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3498. Min Range: -9.3498
Max Act: 8.9123. Min Act: -0.1700
Data Index: 7172257 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3498. Min Range: -9.3498
Max Act: 8.7873. Min Act: -0.1700
Data Index: 6620367 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3498. Min Range: -9.3498
Max Act: 8.7873. Min Act: -0.1700
Data Index: 8125430 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3498. Min Range: -9.3498
Max Act: 8.7873. Min Act: -0.1700
Data Index: 8331613 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3498. Min Range: -9.3498
Max Act: 8.7873. Min Act: -0.1700
Data Index: 5778273 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3498. Min Range: -9.3498
Max Act: 8.7248. Min Act: -0.1700
Data Index: 1392593 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3498. Min Range: -9.3498
Max Act: 8.6623. Min Act: -0.1700
Data Index: 6601113 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3498. Min Range: -9.3498
Max Act: 8.5998. Min Act: -0.1700
Data Index: 3788991 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3498. Min Range: -9.3498
Max Act: 8.5998. Min Act: -0.1700
Data Index: 3956492 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3498. Min Range: -9.3498
Max Act: 8.5373. Min Act: -0.1700
Data Index: 5953157 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3498. Min Range: -9.3498
Max Act: 8.5373. Min Act: -0.1700
Data Index: 4625683 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3498. Min Range: -9.3498
Max Act: 8.4748. Min Act: -0.1700
Data Index: 8756750 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3498. Min Range: -9.3498
Max Act: 8.4748. Min Act: -0.1700
Data Index: 4631200 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3498. Min Range: -9.3498
Max Act: 8.4748. Min Act: -0.1700
Data Index: 8646869 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3498. Min Range: -9.3498
Max Act: 8.4123. Min Act: -0.1700
Data Index: 5982361 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3498. Min Range: -9.3498
Max Act: 8.4123. Min Act: -0.1700
Data Index: 7161902 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3498. Min Range: -9.3498
Max Act: 8.3185. Min Act: -0.1700
Data Index: 1624194 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19