Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2089 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5583. Min Range: -6.5583
Max Act: 6.5583. Min Act: -0.1700
Data Index: 3117227 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5583. Min Range: -6.5583
Max Act: 6.3708. Min Act: -0.1700
Data Index: 5322036 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5583. Min Range: -6.5583
Max Act: 6.2145. Min Act: -0.1700
Data Index: 1225521 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5583. Min Range: -6.5583
Max Act: 6.1833. Min Act: -0.1700
Data Index: 8247704 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5583. Min Range: -6.5583
Max Act: 6.1833. Min Act: -0.1700
Data Index: 6303790 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5583. Min Range: -6.5583
Max Act: 6.1833. Min Act: -0.1700
Data Index: 5455560 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5583. Min Range: -6.5583
Max Act: 6.1520. Min Act: -0.1700
Data Index: 46103 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5583. Min Range: -6.5583
Max Act: 6.1208. Min Act: -0.1700
Data Index: 3239939 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5583. Min Range: -6.5583
Max Act: 6.1208. Min Act: -0.1700
Data Index: 7999702 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5583. Min Range: -6.5583
Max Act: 6.0895. Min Act: -0.1700
Data Index: 5097195 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5583. Min Range: -6.5583
Max Act: 6.0895. Min Act: -0.1700
Data Index: 1380832 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5583. Min Range: -6.5583
Max Act: 6.0270. Min Act: -0.1700
Data Index: 6634449 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5583. Min Range: -6.5583
Max Act: 6.0270. Min Act: -0.1700
Data Index: 3869433 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5583. Min Range: -6.5583
Max Act: 5.9958. Min Act: -0.1700
Data Index: 5302188 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5583. Min Range: -6.5583
Max Act: 5.9958. Min Act: -0.1700
Data Index: 6818108 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5583. Min Range: -6.5583
Max Act: 5.9645. Min Act: -0.1700
Data Index: 2310822 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5583. Min Range: -6.5583
Max Act: 5.9333. Min Act: -0.1700
Data Index: 2012267 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5583. Min Range: -6.5583
Max Act: 5.9333. Min Act: -0.1700
Data Index: 1007216 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5583. Min Range: -6.5583
Max Act: 5.9645. Min Act: -0.1699
Data Index: 3539575 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5583. Min Range: -6.5583
Max Act: 5.9020. Min Act: -0.1700
Data Index: 1983456 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19