Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 35 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1625. Min Range: -7.1625
Max Act: 7.1625. Min Act: -0.1700
Data Index: 4362457 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1625. Min Range: -7.1625
Max Act: 7.0687. Min Act: -0.1700
Data Index: 4754365 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.8812. Min Act: -0.1700
Data Index: 3814683 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.7875. Min Act: -0.1700
Data Index: 321412 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.7875. Min Act: -0.1700
Data Index: 2374892 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.8187. Min Act: -0.1700
Data Index: 4160727 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.7250. Min Act: -0.1700
Data Index: 1442398 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.7250. Min Act: -0.1700
Data Index: 1791426 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.6625. Min Act: -0.1700
Data Index: 439783 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.6312. Min Act: -0.1700
Data Index: 2111781 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.6312. Min Act: -0.1700
Data Index: 6702332 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.5375. Min Act: -0.1700
Data Index: 2196480 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.5375. Min Act: -0.1700
Data Index: 6390569 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.5375. Min Act: -0.1700
Data Index: 3050110 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.5062. Min Act: -0.1700
Data Index: 3267409 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.5062. Min Act: -0.1700
Data Index: 3024440 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.5062. Min Act: -0.1700
Data Index: 7950512 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.5062. Min Act: -0.1700
Data Index: 8389849 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.4750. Min Act: -0.1700
Data Index: 2464971 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.4437. Min Act: -0.1700
Data Index: 932992 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19