Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3081 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0522. Min Range: -5.0522
Max Act: 5.0522. Min Act: -0.1700
Data Index: 3384336 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0522. Min Range: -5.0522
Max Act: 4.9897. Min Act: -0.1700
Data Index: 7492815 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0522. Min Range: -5.0522
Max Act: 4.9272. Min Act: -0.1700
Data Index: 7904332 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0522. Min Range: -5.0522
Max Act: 4.9272. Min Act: -0.1700
Data Index: 6447195 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0522. Min Range: -5.0522
Max Act: 4.9585. Min Act: -0.1700
Data Index: 8229531 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0522. Min Range: -5.0522
Max Act: 4.8960. Min Act: -0.1700
Data Index: 5259605 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0522. Min Range: -5.0522
Max Act: 4.8960. Min Act: -0.1700
Data Index: 7460213 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0522. Min Range: -5.0522
Max Act: 4.8960. Min Act: -0.1700
Data Index: 1712202 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0522. Min Range: -5.0522
Max Act: 4.8647. Min Act: -0.1700
Data Index: 3335083 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0522. Min Range: -5.0522
Max Act: 4.8647. Min Act: -0.1700
Data Index: 318722 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0522. Min Range: -5.0522
Max Act: 4.8022. Min Act: -0.1700
Data Index: 4560751 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0522. Min Range: -5.0522
Max Act: 4.8335. Min Act: -0.1700
Data Index: 5520051 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0522. Min Range: -5.0522
Max Act: 4.8335. Min Act: -0.1700
Data Index: 1060496 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0522. Min Range: -5.0522
Max Act: 4.8647. Min Act: -0.1700
Data Index: 8039962 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0522. Min Range: -5.0522
Max Act: 4.8022. Min Act: -0.1700
Data Index: 6403694 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0522. Min Range: -5.0522
Max Act: 4.7710. Min Act: -0.1700
Data Index: 7513238 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0522. Min Range: -5.0522
Max Act: 4.8022. Min Act: -0.1700
Data Index: 8632962 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0522. Min Range: -5.0522
Max Act: 4.7710. Min Act: -0.1700
Data Index: 1183457 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0522. Min Range: -5.0522
Max Act: 4.7397. Min Act: -0.1700
Data Index: 8734656 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0522. Min Range: -5.0522
Max Act: 4.8022. Min Act: -0.1700
Data Index: 7876366 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19