Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 945 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0959. Min Range: -4.0959
Max Act: 4.0959. Min Act: -0.1700
Data Index: 20299 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0959. Min Range: -4.0959
Max Act: 4.0021. Min Act: -0.1700
Data Index: 1907603 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0959. Min Range: -4.0959
Max Act: 4.0021. Min Act: -0.1700
Data Index: 4147513 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0959. Min Range: -4.0959
Max Act: 4.0021. Min Act: -0.1700
Data Index: 4942735 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0959. Min Range: -4.0959
Max Act: 4.0021. Min Act: -0.1700
Data Index: 7194709 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0959. Min Range: -4.0959
Max Act: 4.0021. Min Act: -0.1700
Data Index: 6724610 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0959. Min Range: -4.0959
Max Act: 3.9708. Min Act: -0.1700
Data Index: 6274960 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0959. Min Range: -4.0959
Max Act: 3.9708. Min Act: -0.1700
Data Index: 8743208 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0959. Min Range: -4.0959
Max Act: 3.9708. Min Act: -0.1700
Data Index: 8122322 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0959. Min Range: -4.0959
Max Act: 3.9708. Min Act: -0.1700
Data Index: 7635844 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0959. Min Range: -4.0959
Max Act: 3.9708. Min Act: -0.1700
Data Index: 7272961 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0959. Min Range: -4.0959
Max Act: 3.9708. Min Act: -0.1700
Data Index: 6871561 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0959. Min Range: -4.0959
Max Act: 3.9708. Min Act: -0.1700
Data Index: 914616 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0959. Min Range: -4.0959
Max Act: 3.9708. Min Act: -0.1700
Data Index: 5874520 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0959. Min Range: -4.0959
Max Act: 3.9708. Min Act: -0.1700
Data Index: 5797339 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0959. Min Range: -4.0959
Max Act: 3.9708. Min Act: -0.1700
Data Index: 5081119 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0959. Min Range: -4.0959
Max Act: 3.9708. Min Act: -0.1700
Data Index: 4770437 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0959. Min Range: -4.0959
Max Act: 3.9708. Min Act: -0.1700
Data Index: 3854411 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0959. Min Range: -4.0959
Max Act: 3.9396. Min Act: -0.1700
Data Index: 70844 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0959. Min Range: -4.0959
Max Act: 3.9396. Min Act: -0.1700
Data Index: 77402 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19