Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3016 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1017. Min Range: -8.1017
Max Act: 8.1017. Min Act: -0.1700
Data Index: 8337008 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1017. Min Range: -8.1017
Max Act: 7.7267. Min Act: -0.1700
Data Index: 2295735 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1017. Min Range: -8.1017
Max Act: 7.6642. Min Act: -0.1700
Data Index: 7856946 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1017. Min Range: -8.1017
Max Act: 7.6329. Min Act: -0.1700
Data Index: 2463647 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1017. Min Range: -8.1017
Max Act: 7.4767. Min Act: -0.1700
Data Index: 726766 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1017. Min Range: -8.1017
Max Act: 7.4454. Min Act: -0.1700
Data Index: 8528316 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1017. Min Range: -8.1017
Max Act: 7.3204. Min Act: -0.1700
Data Index: 4232291 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1017. Min Range: -8.1017
Max Act: 7.3204. Min Act: -0.1700
Data Index: 6604030 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1017. Min Range: -8.1017
Max Act: 7.2892. Min Act: -0.1700
Data Index: 146432 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1017. Min Range: -8.1017
Max Act: 7.1954. Min Act: -0.1700
Data Index: 4071308 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1017. Min Range: -8.1017
Max Act: 7.1954. Min Act: -0.1700
Data Index: 6834322 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1017. Min Range: -8.1017
Max Act: 7.1642. Min Act: -0.1700
Data Index: 6842609 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1017. Min Range: -8.1017
Max Act: 7.1642. Min Act: -0.1700
Data Index: 8200672 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1017. Min Range: -8.1017
Max Act: 7.1642. Min Act: -0.1700
Data Index: 5232722 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1017. Min Range: -8.1017
Max Act: 7.1329. Min Act: -0.1700
Data Index: 2024298 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1017. Min Range: -8.1017
Max Act: 7.1329. Min Act: -0.1700
Data Index: 4855382 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1017. Min Range: -8.1017
Max Act: 7.1017. Min Act: -0.1700
Data Index: 635320 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1017. Min Range: -8.1017
Max Act: 7.1017. Min Act: -0.1700
Data Index: 8153944 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1017. Min Range: -8.1017
Max Act: 7.1017. Min Act: -0.1700
Data Index: 7055928 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1017. Min Range: -8.1017
Max Act: 7.1017. Min Act: -0.1700
Data Index: 6312788 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19