Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3645 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5569. Min Range: -5.5569
Max Act: 5.5569. Min Act: -0.1700
Data Index: 6645388 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5569. Min Range: -5.5569
Max Act: 5.3382. Min Act: -0.1700
Data Index: 2798930 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5569. Min Range: -5.5569
Max Act: 5.2132. Min Act: -0.1700
Data Index: 4312976 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5569. Min Range: -5.5569
Max Act: 5.0882. Min Act: -0.1700
Data Index: 3881486 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5569. Min Range: -5.5569
Max Act: 5.0882. Min Act: -0.1700
Data Index: 1248894 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5569. Min Range: -5.5569
Max Act: 5.0257. Min Act: -0.1700
Data Index: 8178900 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5569. Min Range: -5.5569
Max Act: 4.9944. Min Act: -0.1700
Data Index: 1094884 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5569. Min Range: -5.5569
Max Act: 4.9944. Min Act: -0.1700
Data Index: 1196520 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5569. Min Range: -5.5569
Max Act: 4.9944. Min Act: -0.1700
Data Index: 3584990 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5569. Min Range: -5.5569
Max Act: 4.9944. Min Act: -0.1700
Data Index: 329656 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5569. Min Range: -5.5569
Max Act: 4.9632. Min Act: -0.1700
Data Index: 4592679 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5569. Min Range: -5.5569
Max Act: 4.9632. Min Act: -0.1700
Data Index: 8554088 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5569. Min Range: -5.5569
Max Act: 4.9632. Min Act: -0.1700
Data Index: 7746844 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5569. Min Range: -5.5569
Max Act: 4.9632. Min Act: -0.1700
Data Index: 761401 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5569. Min Range: -5.5569
Max Act: 4.9632. Min Act: -0.1700
Data Index: 7855503 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5569. Min Range: -5.5569
Max Act: 4.9632. Min Act: -0.1700
Data Index: 6789334 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5569. Min Range: -5.5569
Max Act: 4.9632. Min Act: -0.1700
Data Index: 2538641 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5569. Min Range: -5.5569
Max Act: 4.9319. Min Act: -0.1700
Data Index: 8675432 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5569. Min Range: -5.5569
Max Act: 4.9007. Min Act: -0.1700
Data Index: 5547088 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5569. Min Range: -5.5569
Max Act: 4.9007. Min Act: -0.1700
Data Index: 5722567 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19