Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1750 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1469. Min Range: -4.1469
Max Act: 4.1469. Min Act: -0.1700
Data Index: 323350 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1469. Min Range: -4.1469
Max Act: 4.1156. Min Act: -0.1700
Data Index: 2260311 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1469. Min Range: -4.1469
Max Act: 4.0531. Min Act: -0.1700
Data Index: 5688570 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1469. Min Range: -4.1469
Max Act: 4.0218. Min Act: -0.1700
Data Index: 4583113 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1469. Min Range: -4.1469
Max Act: 4.0218. Min Act: -0.1700
Data Index: 7890955 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1469. Min Range: -4.1469
Max Act: 4.0218. Min Act: -0.1700
Data Index: 1680658 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1469. Min Range: -4.1469
Max Act: 3.9906. Min Act: -0.1700
Data Index: 3167978 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1469. Min Range: -4.1469
Max Act: 3.9593. Min Act: -0.1700
Data Index: 2260309 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1469. Min Range: -4.1469
Max Act: 3.9280. Min Act: -0.1700
Data Index: 2982788 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1469. Min Range: -4.1469
Max Act: 3.9280. Min Act: -0.1700
Data Index: 6832192 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1469. Min Range: -4.1469
Max Act: 3.9280. Min Act: -0.1700
Data Index: 1110053 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1469. Min Range: -4.1469
Max Act: 3.9280. Min Act: -0.1700
Data Index: 3445026 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1469. Min Range: -4.1469
Max Act: 3.8655. Min Act: -0.1700
Data Index: 2530973 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1469. Min Range: -4.1469
Max Act: 3.8655. Min Act: -0.1700
Data Index: 2721551 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1469. Min Range: -4.1469
Max Act: 3.8342. Min Act: -0.1700
Data Index: 7605116 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1469. Min Range: -4.1469
Max Act: 3.8499. Min Act: -0.1700
Data Index: 2361342 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1469. Min Range: -4.1469
Max Act: 3.8655. Min Act: -0.1700
Data Index: 8539064 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1469. Min Range: -4.1469
Max Act: 3.8342. Min Act: -0.1700
Data Index: 7704289 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1469. Min Range: -4.1469
Max Act: 3.8342. Min Act: -0.1700
Data Index: 6479064 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1469. Min Range: -4.1469
Max Act: 3.8342. Min Act: -0.1700
Data Index: 5373225 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19