Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1096 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3919. Min Range: -5.3919
Max Act: 5.3919. Min Act: -0.1700
Data Index: 8447276 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3919. Min Range: -5.3919
Max Act: 5.3919. Min Act: -0.1700
Data Index: 8447236 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3919. Min Range: -5.3919
Max Act: 5.0169. Min Act: -0.1700
Data Index: 641355 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3919. Min Range: -5.3919
Max Act: 5.0169. Min Act: -0.1700
Data Index: 784689 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3919. Min Range: -5.3919
Max Act: 4.9857. Min Act: -0.1700
Data Index: 3868734 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3919. Min Range: -5.3919
Max Act: 4.9232. Min Act: -0.1700
Data Index: 1886549 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3919. Min Range: -5.3919
Max Act: 4.9232. Min Act: -0.1700
Data Index: 3868768 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3919. Min Range: -5.3919
Max Act: 4.8607. Min Act: -0.1700
Data Index: 2139631 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3919. Min Range: -5.3919
Max Act: 4.8607. Min Act: -0.1700
Data Index: 3868767 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3919. Min Range: -5.3919
Max Act: 4.8294. Min Act: -0.1700
Data Index: 6161688 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3919. Min Range: -5.3919
Max Act: 4.7982. Min Act: -0.1700
Data Index: 4889531 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3919. Min Range: -5.3919
Max Act: 4.7669. Min Act: -0.1700
Data Index: 2829625 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3919. Min Range: -5.3919
Max Act: 4.7982. Min Act: -0.1700
Data Index: 8694452 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3919. Min Range: -5.3919
Max Act: 4.6732. Min Act: -0.1700
Data Index: 5888690 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3919. Min Range: -5.3919
Max Act: 4.7357. Min Act: -0.1697
Data Index: 240660 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3919. Min Range: -5.3919
Max Act: 4.7357. Min Act: -0.1700
Data Index: 4734109 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3919. Min Range: -5.3919
Max Act: 4.7044. Min Act: -0.1700
Data Index: 3775341 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3919. Min Range: -5.3919
Max Act: 4.7357. Min Act: -0.1700
Data Index: 992539 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3919. Min Range: -5.3919
Max Act: 4.7044. Min Act: -0.1700
Data Index: 5821873 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3919. Min Range: -5.3919
Max Act: 4.6732. Min Act: -0.1700
Data Index: 2919559 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19