Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 53 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2811. Min Range: -6.2811
Max Act: 6.2811. Min Act: -0.1700
Data Index: 5749782 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2811. Min Range: -6.2811
Max Act: 6.1874. Min Act: -0.1700
Data Index: 3525732 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2811. Min Range: -6.2811
Max Act: 6.1561. Min Act: -0.1700
Data Index: 608040 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2811. Min Range: -6.2811
Max Act: 6.0624. Min Act: -0.1700
Data Index: 1327734 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2811. Min Range: -6.2811
Max Act: 6.0624. Min Act: -0.1700
Data Index: 2736794 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2811. Min Range: -6.2811
Max Act: 6.0311. Min Act: -0.1700
Data Index: 2630404 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.9686. Min Act: -0.1700
Data Index: 3871981 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.8749. Min Act: -0.1700
Data Index: 1175454 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.8749. Min Act: -0.1700
Data Index: 2714160 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.8749. Min Act: -0.1700
Data Index: 2907851 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.8436. Min Act: -0.1700
Data Index: 8517191 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.8436. Min Act: -0.1700
Data Index: 2062484 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.8124. Min Act: -0.1700
Data Index: 1070455 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.8124. Min Act: -0.1700
Data Index: 3408155 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.7811. Min Act: -0.1700
Data Index: 3220913 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.7811. Min Act: -0.1700
Data Index: 2321369 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.7811. Min Act: -0.1700
Data Index: 7413947 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.7499. Min Act: -0.1700
Data Index: 5511171 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.7499. Min Act: -0.1700
Data Index: 3954886 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.7499. Min Act: -0.1700
Data Index: 4965154 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19