Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3199 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7931. Min Range: -5.7931
Max Act: 5.7931. Min Act: -0.1700
Data Index: 8760543 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7931. Min Range: -5.7931
Max Act: 5.7931. Min Act: -0.1700
Data Index: 8489966 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7931. Min Range: -5.7931
Max Act: 5.6681. Min Act: -0.1692
Data Index: 259980 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7931. Min Range: -5.7931
Max Act: 5.6368. Min Act: -0.1700
Data Index: 6936929 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7931. Min Range: -5.7931
Max Act: 5.4181. Min Act: -0.1700
Data Index: 3491735 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7931. Min Range: -5.7931
Max Act: 5.3243. Min Act: -0.1700
Data Index: 2851240 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7931. Min Range: -5.7931
Max Act: 5.2931. Min Act: -0.1700
Data Index: 258870 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7931. Min Range: -5.7931
Max Act: 5.2931. Min Act: -0.1700
Data Index: 880245 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7931. Min Range: -5.7931
Max Act: 5.1368. Min Act: -0.1700
Data Index: 3962659 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7931. Min Range: -5.7931
Max Act: 5.1368. Min Act: -0.1700
Data Index: 258864 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7931. Min Range: -5.7931
Max Act: 5.1056. Min Act: -0.1700
Data Index: 4082422 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7931. Min Range: -5.7931
Max Act: 5.0743. Min Act: -0.1700
Data Index: 2312323 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7931. Min Range: -5.7931
Max Act: 5.0743. Min Act: -0.1700
Data Index: 7914072 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7931. Min Range: -5.7931
Max Act: 5.0743. Min Act: -0.1700
Data Index: 4503578 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7931. Min Range: -5.7931
Max Act: 5.0431. Min Act: -0.1700
Data Index: 1776375 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7931. Min Range: -5.7931
Max Act: 5.0431. Min Act: -0.1700
Data Index: 705068 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7931. Min Range: -5.7931
Max Act: 5.0118. Min Act: -0.1700
Data Index: 341250 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7931. Min Range: -5.7931
Max Act: 5.0431. Min Act: -0.1700
Data Index: 2706555 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7931. Min Range: -5.7931
Max Act: 5.0118. Min Act: -0.1700
Data Index: 2851241 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7931. Min Range: -5.7931
Max Act: 5.0118. Min Act: -0.1700
Data Index: 8364167 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19