Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2358 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7618. Min Range: -4.7618
Max Act: 4.7618. Min Act: -0.1700
Data Index: 295484 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7618. Min Range: -4.7618
Max Act: 4.5743. Min Act: -0.1700
Data Index: 983807 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7618. Min Range: -4.7618
Max Act: 4.4806. Min Act: -0.1700
Data Index: 8691032 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7618. Min Range: -4.7618
Max Act: 4.4493. Min Act: -0.1700
Data Index: 5657685 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7618. Min Range: -4.7618
Max Act: 4.4493. Min Act: -0.1700
Data Index: 5421200 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7618. Min Range: -4.7618
Max Act: 4.4181. Min Act: -0.1700
Data Index: 2893605 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7618. Min Range: -4.7618
Max Act: 4.3868. Min Act: -0.1700
Data Index: 5191554 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7618. Min Range: -4.7618
Max Act: 4.3556. Min Act: -0.1700
Data Index: 4360264 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7618. Min Range: -4.7618
Max Act: 4.3243. Min Act: -0.1700
Data Index: 3485139 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7618. Min Range: -4.7618
Max Act: 4.3243. Min Act: -0.1700
Data Index: 5035365 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7618. Min Range: -4.7618
Max Act: 4.3243. Min Act: -0.1700
Data Index: 3857291 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7618. Min Range: -4.7618
Max Act: 4.3243. Min Act: -0.1700
Data Index: 829603 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7618. Min Range: -4.7618
Max Act: 4.2931. Min Act: -0.1700
Data Index: 7972541 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7618. Min Range: -4.7618
Max Act: 4.2931. Min Act: -0.1700
Data Index: 7558159 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7618. Min Range: -4.7618
Max Act: 4.2931. Min Act: -0.1700
Data Index: 4216650 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7618. Min Range: -4.7618
Max Act: 4.2618. Min Act: -0.1700
Data Index: 4791562 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7618. Min Range: -4.7618
Max Act: 4.2931. Min Act: -0.1700
Data Index: 5229318 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7618. Min Range: -4.7618
Max Act: 4.2306. Min Act: -0.1700
Data Index: 2303125 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7618. Min Range: -4.7618
Max Act: 4.2618. Min Act: -0.1700
Data Index: 2883568 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7618. Min Range: -4.7618
Max Act: 4.2618. Min Act: -0.1700
Data Index: 4943920 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19