Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3252 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0648. Min Range: -7.0648
Max Act: 7.0648. Min Act: -0.1700
Data Index: 7826418 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0648. Min Range: -7.0648
Max Act: 6.9085. Min Act: -0.1700
Data Index: 6865131 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0648. Min Range: -7.0648
Max Act: 6.7210. Min Act: -0.1700
Data Index: 2819851 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0648. Min Range: -7.0648
Max Act: 6.7210. Min Act: -0.1700
Data Index: 4769725 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0648. Min Range: -7.0648
Max Act: 6.6273. Min Act: -0.1700
Data Index: 388362 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0648. Min Range: -7.0648
Max Act: 6.5335. Min Act: -0.1700
Data Index: 1443744 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0648. Min Range: -7.0648
Max Act: 6.5335. Min Act: -0.1700
Data Index: 7412240 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0648. Min Range: -7.0648
Max Act: 6.5335. Min Act: -0.1700
Data Index: 8128424 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0648. Min Range: -7.0648
Max Act: 6.4398. Min Act: -0.1700
Data Index: 1775391 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0648. Min Range: -7.0648
Max Act: 6.3460. Min Act: -0.1700
Data Index: 67007 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0648. Min Range: -7.0648
Max Act: 6.3148. Min Act: -0.1700
Data Index: 8111334 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0648. Min Range: -7.0648
Max Act: 6.2523. Min Act: -0.1700
Data Index: 2942618 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0648. Min Range: -7.0648
Max Act: 6.2835. Min Act: -0.1700
Data Index: 8601288 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0648. Min Range: -7.0648
Max Act: 6.2523. Min Act: -0.1700
Data Index: 3495747 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0648. Min Range: -7.0648
Max Act: 6.2523. Min Act: -0.1700
Data Index: 5094560 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0648. Min Range: -7.0648
Max Act: 6.2835. Min Act: -0.1700
Data Index: 974680 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0648. Min Range: -7.0648
Max Act: 6.1898. Min Act: -0.1700
Data Index: 2600955 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0648. Min Range: -7.0648
Max Act: 6.1585. Min Act: -0.1700
Data Index: 3656730 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0648. Min Range: -7.0648
Max Act: 6.1898. Min Act: -0.1700
Data Index: 1917959 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0648. Min Range: -7.0648
Max Act: 6.1585. Min Act: -0.1700
Data Index: 7060910 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19