Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3125 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6702. Min Range: -6.6702
Max Act: 6.6702. Min Act: -0.1700
Data Index: 736103 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6702. Min Range: -6.6702
Max Act: 6.6702. Min Act: -0.1700
Data Index: 6040801 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6702. Min Range: -6.6702
Max Act: 6.6389. Min Act: -0.1700
Data Index: 3328044 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6702. Min Range: -6.6702
Max Act: 6.6077. Min Act: -0.1700
Data Index: 8749105 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6702. Min Range: -6.6702
Max Act: 6.5764. Min Act: -0.1700
Data Index: 4046281 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6702. Min Range: -6.6702
Max Act: 6.4827. Min Act: -0.1700
Data Index: 1064689 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6702. Min Range: -6.6702
Max Act: 6.4827. Min Act: -0.1700
Data Index: 7195898 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6702. Min Range: -6.6702
Max Act: 6.5139. Min Act: -0.1700
Data Index: 3704320 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6702. Min Range: -6.6702
Max Act: 6.4827. Min Act: -0.1700
Data Index: 1456743 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6702. Min Range: -6.6702
Max Act: 6.4827. Min Act: -0.1700
Data Index: 6889773 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6702. Min Range: -6.6702
Max Act: 6.4827. Min Act: -0.1700
Data Index: 2814144 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6702. Min Range: -6.6702
Max Act: 6.4514. Min Act: -0.1700
Data Index: 7634463 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6702. Min Range: -6.6702
Max Act: 6.4514. Min Act: -0.1700
Data Index: 1305010 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6702. Min Range: -6.6702
Max Act: 6.3889. Min Act: -0.1700
Data Index: 6418517 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6702. Min Range: -6.6702
Max Act: 6.4202. Min Act: -0.1700
Data Index: 1914398 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6702. Min Range: -6.6702
Max Act: 6.4202. Min Act: -0.1700
Data Index: 3611919 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6702. Min Range: -6.6702
Max Act: 6.4202. Min Act: -0.1700
Data Index: 6596793 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6702. Min Range: -6.6702
Max Act: 6.4202. Min Act: -0.1700
Data Index: 4192667 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6702. Min Range: -6.6702
Max Act: 6.4202. Min Act: -0.1700
Data Index: 6731444 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6702. Min Range: -6.6702
Max Act: 6.3889. Min Act: -0.1700
Data Index: 4173465 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19