Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3473 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1306. Min Range: -5.1306
Max Act: 5.1306. Min Act: -0.1700
Data Index: 2745517 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1306. Min Range: -5.1306
Max Act: 5.0368. Min Act: -0.1700
Data Index: 2175993 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1306. Min Range: -5.1306
Max Act: 5.0056. Min Act: -0.1700
Data Index: 6799503 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1306. Min Range: -5.1306
Max Act: 4.9743. Min Act: -0.1700
Data Index: 401666 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1306. Min Range: -5.1306
Max Act: 4.9431. Min Act: -0.1700
Data Index: 408203 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1306. Min Range: -5.1306
Max Act: 4.9118. Min Act: -0.1700
Data Index: 2125901 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1306. Min Range: -5.1306
Max Act: 4.8806. Min Act: -0.1700
Data Index: 3167627 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1306. Min Range: -5.1306
Max Act: 4.8806. Min Act: -0.1700
Data Index: 4734144 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1306. Min Range: -5.1306
Max Act: 4.8493. Min Act: -0.1700
Data Index: 2815610 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1306. Min Range: -5.1306
Max Act: 4.8181. Min Act: -0.1700
Data Index: 4110685 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1306. Min Range: -5.1306
Max Act: 4.8181. Min Act: -0.1700
Data Index: 7912400 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1306. Min Range: -5.1306
Max Act: 4.7868. Min Act: -0.1700
Data Index: 7885785 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1306. Min Range: -5.1306
Max Act: 4.7868. Min Act: -0.1700
Data Index: 1304244 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1306. Min Range: -5.1306
Max Act: 4.7868. Min Act: -0.1700
Data Index: 7345989 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1306. Min Range: -5.1306
Max Act: 4.7868. Min Act: -0.1700
Data Index: 8473041 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1306. Min Range: -5.1306
Max Act: 4.7556. Min Act: -0.1700
Data Index: 2379103 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1306. Min Range: -5.1306
Max Act: 4.7556. Min Act: -0.1700
Data Index: 4508803 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1306. Min Range: -5.1306
Max Act: 4.7556. Min Act: -0.1700
Data Index: 705657 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1306. Min Range: -5.1306
Max Act: 4.7556. Min Act: -0.1700
Data Index: 2745518 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1306. Min Range: -5.1306
Max Act: 4.7556. Min Act: -0.1700
Data Index: 1659779 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19