Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2686 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 7.3022. Min Range: -7.3022
Max Act: 7.3022. Min Act: -0.1700
Data Index: 6169085 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3022. Min Range: -7.3022
Max Act: 7.1459. Min Act: -0.1700
Data Index: 3329517 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3022. Min Range: -7.3022
Max Act: 7.0522. Min Act: -0.1700
Data Index: 484770 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3022. Min Range: -7.3022
Max Act: 7.0209. Min Act: -0.1700
Data Index: 585660 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3022. Min Range: -7.3022
Max Act: 6.9897. Min Act: -0.1700
Data Index: 8048366 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3022. Min Range: -7.3022
Max Act: 6.8959. Min Act: -0.1700
Data Index: 2152362 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3022. Min Range: -7.3022
Max Act: 6.8959. Min Act: -0.1700
Data Index: 1656362 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3022. Min Range: -7.3022
Max Act: 6.8959. Min Act: -0.1700
Data Index: 3269803 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3022. Min Range: -7.3022
Max Act: 6.8959. Min Act: -0.1700
Data Index: 1596785 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3022. Min Range: -7.3022
Max Act: 6.9272. Min Act: -0.1700
Data Index: 2899860 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3022. Min Range: -7.3022
Max Act: 6.8959. Min Act: -0.1700
Data Index: 4391794 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3022. Min Range: -7.3022
Max Act: 6.8647. Min Act: -0.1700
Data Index: 2322753 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3022. Min Range: -7.3022
Max Act: 6.8647. Min Act: -0.1700
Data Index: 7803648 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3022. Min Range: -7.3022
Max Act: 6.8647. Min Act: -0.1700
Data Index: 5572067 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3022. Min Range: -7.3022
Max Act: 6.8022. Min Act: -0.1700
Data Index: 1264135 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3022. Min Range: -7.3022
Max Act: 6.7709. Min Act: -0.1700
Data Index: 2055351 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3022. Min Range: -7.3022
Max Act: 6.8334. Min Act: -0.1700
Data Index: 3351612 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3022. Min Range: -7.3022
Max Act: 6.8022. Min Act: -0.1700
Data Index: 7308033 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3022. Min Range: -7.3022
Max Act: 6.8022. Min Act: -0.1700
Data Index: 6134487 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3022. Min Range: -7.3022
Max Act: 6.7709. Min Act: -0.1700
Data Index: 5013027 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19