Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 607 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8435. Min Range: -4.8435
Max Act: 4.8435. Min Act: -0.1700
Data Index: 7931132 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8435. Min Range: -4.8435
Max Act: 4.8435. Min Act: -0.1700
Data Index: 4932461 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8435. Min Range: -4.8435
Max Act: 4.7810. Min Act: -0.1700
Data Index: 60922 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8435. Min Range: -4.8435
Max Act: 4.7810. Min Act: -0.1700
Data Index: 5757244 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8435. Min Range: -4.8435
Max Act: 4.7810. Min Act: -0.1700
Data Index: 7560798 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8435. Min Range: -4.8435
Max Act: 4.7810. Min Act: -0.1700
Data Index: 7190354 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8435. Min Range: -4.8435
Max Act: 4.7810. Min Act: -0.1700
Data Index: 8099010 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8435. Min Range: -4.8435
Max Act: 4.7497. Min Act: -0.1700
Data Index: 4023362 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8435. Min Range: -4.8435
Max Act: 4.7497. Min Act: -0.1700
Data Index: 5680709 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8435. Min Range: -4.8435
Max Act: 4.7185. Min Act: -0.1700
Data Index: 2884953 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8435. Min Range: -4.8435
Max Act: 4.7185. Min Act: -0.1700
Data Index: 8371943 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8435. Min Range: -4.8435
Max Act: 4.7185. Min Act: -0.1700
Data Index: 5778729 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8435. Min Range: -4.8435
Max Act: 4.6872. Min Act: -0.1700
Data Index: 7745149 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8435. Min Range: -4.8435
Max Act: 4.6560. Min Act: -0.1700
Data Index: 4950441 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8435. Min Range: -4.8435
Max Act: 4.6560. Min Act: -0.1700
Data Index: 953625 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8435. Min Range: -4.8435
Max Act: 4.6247. Min Act: -0.1700
Data Index: 7131257 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8435. Min Range: -4.8435
Max Act: 4.6247. Min Act: -0.1700
Data Index: 4723802 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8435. Min Range: -4.8435
Max Act: 4.6247. Min Act: -0.1700
Data Index: 3974201 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8435. Min Range: -4.8435
Max Act: 4.6247. Min Act: -0.1700
Data Index: 5267558 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8435. Min Range: -4.8435
Max Act: 4.6247. Min Act: -0.1700
Data Index: 5297867 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19