Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2592 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1799. Min Range: -6.1799
Max Act: 6.1799. Min Act: -0.1700
Data Index: 7622441 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1799. Min Range: -6.1799
Max Act: 5.9924. Min Act: -0.1700
Data Index: 1662498 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1799. Min Range: -6.1799
Max Act: 5.9924. Min Act: -0.1700
Data Index: 6250535 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1799. Min Range: -6.1799
Max Act: 5.9299. Min Act: -0.1700
Data Index: 3168963 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1799. Min Range: -6.1799
Max Act: 5.9612. Min Act: -0.1700
Data Index: 5449982 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1799. Min Range: -6.1799
Max Act: 5.9299. Min Act: -0.1700
Data Index: 6417651 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1799. Min Range: -6.1799
Max Act: 5.8987. Min Act: -0.1700
Data Index: 5048800 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1799. Min Range: -6.1799
Max Act: 5.8674. Min Act: -0.1700
Data Index: 237786 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1799. Min Range: -6.1799
Max Act: 5.8674. Min Act: -0.1700
Data Index: 3546055 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1799. Min Range: -6.1799
Max Act: 5.8362. Min Act: -0.1700
Data Index: 6152114 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1799. Min Range: -6.1799
Max Act: 5.8049. Min Act: -0.1700
Data Index: 3136245 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1799. Min Range: -6.1799
Max Act: 5.8362. Min Act: -0.1700
Data Index: 6681823 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1799. Min Range: -6.1799
Max Act: 5.7737. Min Act: -0.1700
Data Index: 6170311 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1799. Min Range: -6.1799
Max Act: 5.7737. Min Act: -0.1700
Data Index: 611337 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1799. Min Range: -6.1799
Max Act: 5.7112. Min Act: -0.1700
Data Index: 4518735 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1799. Min Range: -6.1799
Max Act: 5.7737. Min Act: -0.1700
Data Index: 4075565 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1799. Min Range: -6.1799
Max Act: 5.7424. Min Act: -0.1700
Data Index: 1175192 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1799. Min Range: -6.1799
Max Act: 5.7424. Min Act: -0.1700
Data Index: 599259 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1799. Min Range: -6.1799
Max Act: 5.7424. Min Act: -0.1700
Data Index: 551925 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1799. Min Range: -6.1799
Max Act: 5.7737. Min Act: -0.1700
Data Index: 3515880 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19