Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 910 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0016. Min Range: -3.0016
Max Act: 3.0016. Min Act: -0.1700
Data Index: 8698792 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0016. Min Range: -3.0016
Max Act: 2.9700. Min Act: -0.1700
Data Index: 2955254 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0016. Min Range: -3.0016
Max Act: 2.9700. Min Act: -0.1700
Data Index: 1036994 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0016. Min Range: -3.0016
Max Act: 2.9542. Min Act: -0.1700
Data Index: 6619216 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0016. Min Range: -3.0016
Max Act: 2.9542. Min Act: -0.1700
Data Index: 5397879 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0016. Min Range: -3.0016
Max Act: 2.9542. Min Act: -0.1700
Data Index: 4742338 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0016. Min Range: -3.0016
Max Act: 2.9542. Min Act: -0.1700
Data Index: 3594237 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0016. Min Range: -3.0016
Max Act: 2.9542. Min Act: -0.1700
Data Index: 3479421 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0016. Min Range: -3.0016
Max Act: 2.9384. Min Act: -0.1700
Data Index: 8563872 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0016. Min Range: -3.0016
Max Act: 2.9384. Min Act: -0.1700
Data Index: 3146433 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0016. Min Range: -3.0016
Max Act: 2.9225. Min Act: -0.1700
Data Index: 7054816 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0016. Min Range: -3.0016
Max Act: 2.9225. Min Act: -0.1700
Data Index: 124208 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0016. Min Range: -3.0016
Max Act: 2.9225. Min Act: -0.1700
Data Index: 1125368 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0016. Min Range: -3.0016
Max Act: 2.9225. Min Act: -0.1700
Data Index: 6278933 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0016. Min Range: -3.0016
Max Act: 2.9067. Min Act: -0.1700
Data Index: 1782640 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0016. Min Range: -3.0016
Max Act: 2.9225. Min Act: -0.1700
Data Index: 1125362 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0016. Min Range: -3.0016
Max Act: 2.9067. Min Act: -0.1700
Data Index: 4274008 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0016. Min Range: -3.0016
Max Act: 2.8908. Min Act: -0.1700
Data Index: 1061260 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0016. Min Range: -3.0016
Max Act: 2.8908. Min Act: -0.1700
Data Index: 4478046 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0016. Min Range: -3.0016
Max Act: 2.8908. Min Act: -0.1700
Data Index: 2470764 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19