Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2307 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2147. Min Range: -6.2147
Max Act: 6.2147. Min Act: -0.1700
Data Index: 818410 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2147. Min Range: -6.2147
Max Act: 6.1834. Min Act: -0.1700
Data Index: 7675817 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2147. Min Range: -6.2147
Max Act: 6.0897. Min Act: -0.1700
Data Index: 7612433 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2147. Min Range: -6.2147
Max Act: 6.1209. Min Act: -0.1700
Data Index: 453682 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2147. Min Range: -6.2147
Max Act: 6.0897. Min Act: -0.1700
Data Index: 4568364 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2147. Min Range: -6.2147
Max Act: 6.0897. Min Act: -0.1700
Data Index: 7185373 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2147. Min Range: -6.2147
Max Act: 5.9647. Min Act: -0.1700
Data Index: 4632598 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2147. Min Range: -6.2147
Max Act: 5.9334. Min Act: -0.1700
Data Index: 6930636 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2147. Min Range: -6.2147
Max Act: 5.9647. Min Act: -0.1700
Data Index: 4521733 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2147. Min Range: -6.2147
Max Act: 5.9647. Min Act: -0.1700
Data Index: 189723 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2147. Min Range: -6.2147
Max Act: 5.9334. Min Act: -0.1700
Data Index: 7046920 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2147. Min Range: -6.2147
Max Act: 5.9334. Min Act: -0.1700
Data Index: 2518423 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2147. Min Range: -6.2147
Max Act: 5.9022. Min Act: -0.1700
Data Index: 8163436 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2147. Min Range: -6.2147
Max Act: 5.8397. Min Act: -0.1700
Data Index: 16042 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2147. Min Range: -6.2147
Max Act: 5.8709. Min Act: -0.1700
Data Index: 5808997 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2147. Min Range: -6.2147
Max Act: 5.8397. Min Act: -0.1700
Data Index: 2360988 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2147. Min Range: -6.2147
Max Act: 5.8397. Min Act: -0.1700
Data Index: 2497607 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2147. Min Range: -6.2147
Max Act: 5.8397. Min Act: -0.1700
Data Index: 6239575 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2147. Min Range: -6.2147
Max Act: 5.8397. Min Act: -0.1700
Data Index: 5440508 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2147. Min Range: -6.2147
Max Act: 5.8397. Min Act: -0.1700
Data Index: 5018457 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19