Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2746 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6642. Min Range: -6.6642
Max Act: 6.6642. Min Act: -0.1700
Data Index: 460956 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6642. Min Range: -6.6642
Max Act: 6.1954. Min Act: -0.1700
Data Index: 7386217 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6642. Min Range: -6.6642
Max Act: 6.1954. Min Act: -0.1700
Data Index: 2613480 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6642. Min Range: -6.6642
Max Act: 6.1329. Min Act: -0.1700
Data Index: 8686001 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6642. Min Range: -6.6642
Max Act: 6.1329. Min Act: -0.1700
Data Index: 7386222 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6642. Min Range: -6.6642
Max Act: 6.1017. Min Act: -0.1700
Data Index: 8208322 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6642. Min Range: -6.6642
Max Act: 6.0704. Min Act: -0.1700
Data Index: 8652107 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6642. Min Range: -6.6642
Max Act: 6.0079. Min Act: -0.1700
Data Index: 1031440 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6642. Min Range: -6.6642
Max Act: 6.0079. Min Act: -0.1700
Data Index: 6481654 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6642. Min Range: -6.6642
Max Act: 6.0079. Min Act: -0.1700
Data Index: 2374249 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6642. Min Range: -6.6642
Max Act: 5.9142. Min Act: -0.1700
Data Index: 5994534 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6642. Min Range: -6.6642
Max Act: 5.9454. Min Act: -0.1700
Data Index: 8158884 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6642. Min Range: -6.6642
Max Act: 5.9454. Min Act: -0.1700
Data Index: 8218613 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6642. Min Range: -6.6642
Max Act: 5.9767. Min Act: -0.1700
Data Index: 7216076 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6642. Min Range: -6.6642
Max Act: 5.9142. Min Act: -0.1700
Data Index: 5867807 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6642. Min Range: -6.6642
Max Act: 5.8829. Min Act: -0.1700
Data Index: 8208317 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6642. Min Range: -6.6642
Max Act: 5.8829. Min Act: -0.1700
Data Index: 5923218 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6642. Min Range: -6.6642
Max Act: 5.8829. Min Act: -0.1700
Data Index: 4908478 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6642. Min Range: -6.6642
Max Act: 5.8829. Min Act: -0.1700
Data Index: 8354506 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6642. Min Range: -6.6642
Max Act: 5.8517. Min Act: -0.1700
Data Index: 4389392 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19