Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5096 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7994. Min Range: -3.7994
Max Act: 3.7994. Min Act: -0.1700
Data Index: 1773218 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7994. Min Range: -3.7994
Max Act: 3.5648. Min Act: -0.1700
Data Index: 486122 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7994. Min Range: -3.7994
Max Act: 3.5491. Min Act: -0.1700
Data Index: 4594578 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7994. Min Range: -3.7994
Max Act: 3.5491. Min Act: -0.1700
Data Index: 6303850 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7994. Min Range: -3.7994
Max Act: 3.5334. Min Act: -0.1700
Data Index: 6417449 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7994. Min Range: -3.7994
Max Act: 3.5491. Min Act: -0.1700
Data Index: 6208383 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7994. Min Range: -3.7994
Max Act: 3.5021. Min Act: -0.1700
Data Index: 8539015 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7994. Min Range: -3.7994
Max Act: 3.4708. Min Act: -0.1700
Data Index: 721215 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7994. Min Range: -3.7994
Max Act: 3.4708. Min Act: -0.1700
Data Index: 2645311 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7994. Min Range: -3.7994
Max Act: 3.4865. Min Act: -0.1700
Data Index: 7904784 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7994. Min Range: -3.7994
Max Act: 3.4551. Min Act: -0.1700
Data Index: 4829937 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7994. Min Range: -3.7994
Max Act: 3.4551. Min Act: -0.1700
Data Index: 2510762 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7994. Min Range: -3.7994
Max Act: 3.4395. Min Act: -0.1700
Data Index: 5943508 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7994. Min Range: -3.7994
Max Act: 3.4395. Min Act: -0.1700
Data Index: 1866127 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7994. Min Range: -3.7994
Max Act: 3.4238. Min Act: -0.1700
Data Index: 2429610 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7994. Min Range: -3.7994
Max Act: 3.4395. Min Act: -0.1700
Data Index: 4234272 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7994. Min Range: -3.7994
Max Act: 3.4395. Min Act: -0.1700
Data Index: 649428 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7994. Min Range: -3.7994
Max Act: 3.4081. Min Act: -0.1700
Data Index: 3441362 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7994. Min Range: -3.7994
Max Act: 3.4238. Min Act: -0.1700
Data Index: 6738936 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7994. Min Range: -3.7994
Max Act: 3.4081. Min Act: -0.1700
Data Index: 7032594 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19