Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3632 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8663. Min Range: -6.8663
Max Act: 6.8663. Min Act: -0.1700
Data Index: 4266078 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8663. Min Range: -6.8663
Max Act: 6.6788. Min Act: -0.1700
Data Index: 5226229 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8663. Min Range: -6.8663
Max Act: 6.6163. Min Act: -0.1700
Data Index: 7019440 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8663. Min Range: -6.8663
Max Act: 6.5851. Min Act: -0.1700
Data Index: 2044478 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8663. Min Range: -6.8663
Max Act: 6.5226. Min Act: -0.1700
Data Index: 8161522 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8663. Min Range: -6.8663
Max Act: 6.4913. Min Act: -0.1700
Data Index: 3969623 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8663. Min Range: -6.8663
Max Act: 6.4913. Min Act: -0.1700
Data Index: 7755773 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8663. Min Range: -6.8663
Max Act: 6.4601. Min Act: -0.1700
Data Index: 6332210 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8663. Min Range: -6.8663
Max Act: 6.4601. Min Act: -0.1700
Data Index: 2870810 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8663. Min Range: -6.8663
Max Act: 6.4288. Min Act: -0.1700
Data Index: 2927304 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8663. Min Range: -6.8663
Max Act: 6.3663. Min Act: -0.1700
Data Index: 2748631 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8663. Min Range: -6.8663
Max Act: 6.4288. Min Act: -0.1700
Data Index: 8666709 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8663. Min Range: -6.8663
Max Act: 6.3663. Min Act: -0.1700
Data Index: 7137183 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8663. Min Range: -6.8663
Max Act: 6.3663. Min Act: -0.1700
Data Index: 1128693 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8663. Min Range: -6.8663
Max Act: 6.3351. Min Act: -0.1700
Data Index: 948176 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8663. Min Range: -6.8663
Max Act: 6.2726. Min Act: -0.1700
Data Index: 238682 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8663. Min Range: -6.8663
Max Act: 6.3038. Min Act: -0.1700
Data Index: 6430028 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8663. Min Range: -6.8663
Max Act: 6.3038. Min Act: -0.1700
Data Index: 1221997 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8663. Min Range: -6.8663
Max Act: 6.3038. Min Act: -0.1700
Data Index: 8080692 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8663. Min Range: -6.8663
Max Act: 6.2726. Min Act: -0.1700
Data Index: 7994500 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19