Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 31 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2752. Min Range: -5.2752
Max Act: 5.2752. Min Act: -0.1700
Data Index: 2455100 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2752. Min Range: -5.2752
Max Act: 5.2440. Min Act: -0.1700
Data Index: 1591663 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2752. Min Range: -5.2752
Max Act: 5.2440. Min Act: -0.1700
Data Index: 2808994 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2752. Min Range: -5.2752
Max Act: 5.2440. Min Act: -0.1696
Data Index: 6792187 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2752. Min Range: -5.2752
Max Act: 5.2127. Min Act: -0.1700
Data Index: 714651 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2752. Min Range: -5.2752
Max Act: 5.2127. Min Act: -0.1700
Data Index: 4769190 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2752. Min Range: -5.2752
Max Act: 5.1815. Min Act: -0.1700
Data Index: 228379 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2752. Min Range: -5.2752
Max Act: 5.1815. Min Act: -0.1700
Data Index: 417099 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2752. Min Range: -5.2752
Max Act: 5.1502. Min Act: -0.1700
Data Index: 6714474 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2752. Min Range: -5.2752
Max Act: 5.1502. Min Act: -0.1700
Data Index: 4700914 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2752. Min Range: -5.2752
Max Act: 5.1815. Min Act: -0.1700
Data Index: 126489 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2752. Min Range: -5.2752
Max Act: 5.1190. Min Act: -0.1700
Data Index: 4525416 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2752. Min Range: -5.2752
Max Act: 5.1190. Min Act: -0.1700
Data Index: 7607323 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2752. Min Range: -5.2752
Max Act: 5.1190. Min Act: -0.1700
Data Index: 8004341 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2752. Min Range: -5.2752
Max Act: 5.1190. Min Act: -0.1700
Data Index: 2663404 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2752. Min Range: -5.2752
Max Act: 5.1190. Min Act: -0.1700
Data Index: 6345133 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2752. Min Range: -5.2752
Max Act: 5.0877. Min Act: -0.1700
Data Index: 279039 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2752. Min Range: -5.2752
Max Act: 5.0877. Min Act: -0.1700
Data Index: 6872783 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2752. Min Range: -5.2752
Max Act: 5.0877. Min Act: -0.1700
Data Index: 2090955 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2752. Min Range: -5.2752
Max Act: 5.0565. Min Act: -0.1700
Data Index: 5555595 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19