Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4282 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0763. Min Range: -7.0763
Max Act: 7.0763. Min Act: -0.1700
Data Index: 2678965 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0763. Min Range: -7.0763
Max Act: 6.9513. Min Act: -0.1700
Data Index: 2400598 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0763. Min Range: -7.0763
Max Act: 6.8888. Min Act: -0.1700
Data Index: 3594817 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0763. Min Range: -7.0763
Max Act: 6.8263. Min Act: -0.1700
Data Index: 7560842 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0763. Min Range: -7.0763
Max Act: 6.7951. Min Act: -0.1700
Data Index: 2414444 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0763. Min Range: -7.0763
Max Act: 6.7638. Min Act: -0.1700
Data Index: 105698 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0763. Min Range: -7.0763
Max Act: 6.7326. Min Act: -0.1700
Data Index: 5992207 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0763. Min Range: -7.0763
Max Act: 6.6701. Min Act: -0.1700
Data Index: 5308975 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0763. Min Range: -7.0763
Max Act: 6.7013. Min Act: -0.1700
Data Index: 5479903 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0763. Min Range: -7.0763
Max Act: 6.6388. Min Act: -0.1700
Data Index: 4021558 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0763. Min Range: -7.0763
Max Act: 6.6388. Min Act: -0.1700
Data Index: 8669263 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0763. Min Range: -7.0763
Max Act: 6.6388. Min Act: -0.1700
Data Index: 5653228 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0763. Min Range: -7.0763
Max Act: 6.6388. Min Act: -0.1700
Data Index: 5425741 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0763. Min Range: -7.0763
Max Act: 6.5763. Min Act: -0.1700
Data Index: 1641648 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0763. Min Range: -7.0763
Max Act: 6.6076. Min Act: -0.1700
Data Index: 6783892 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0763. Min Range: -7.0763
Max Act: 6.5763. Min Act: -0.1700
Data Index: 3102827 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0763. Min Range: -7.0763
Max Act: 6.5763. Min Act: -0.1700
Data Index: 6733697 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0763. Min Range: -7.0763
Max Act: 6.5763. Min Act: -0.1700
Data Index: 3665670 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0763. Min Range: -7.0763
Max Act: 6.5451. Min Act: -0.1700
Data Index: 5647602 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0763. Min Range: -7.0763
Max Act: 6.5763. Min Act: -0.1700
Data Index: 5089448 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19