Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3456 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1589. Min Range: -5.1589
Max Act: 5.1589. Min Act: -0.1700
Data Index: 7024342 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1589. Min Range: -5.1589
Max Act: 5.1589. Min Act: -0.1700
Data Index: 1757706 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1589. Min Range: -5.1589
Max Act: 5.1589. Min Act: -0.1700
Data Index: 7864010 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1589. Min Range: -5.1589
Max Act: 5.1277. Min Act: -0.1700
Data Index: 4524698 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1589. Min Range: -5.1589
Max Act: 5.0652. Min Act: -0.1700
Data Index: 8250725 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1589. Min Range: -5.1589
Max Act: 5.0652. Min Act: -0.1700
Data Index: 422807 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1589. Min Range: -5.1589
Max Act: 5.0339. Min Act: -0.1700
Data Index: 1030968 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1589. Min Range: -5.1589
Max Act: 5.0339. Min Act: -0.1700
Data Index: 347317 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1589. Min Range: -5.1589
Max Act: 5.0027. Min Act: -0.1700
Data Index: 2556568 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1589. Min Range: -5.1589
Max Act: 5.0339. Min Act: -0.1700
Data Index: 1561924 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1589. Min Range: -5.1589
Max Act: 4.9714. Min Act: -0.1700
Data Index: 272640 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1589. Min Range: -5.1589
Max Act: 4.9714. Min Act: -0.1700
Data Index: 5816390 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1589. Min Range: -5.1589
Max Act: 4.9714. Min Act: -0.1700
Data Index: 2363184 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1589. Min Range: -5.1589
Max Act: 4.9402. Min Act: -0.1700
Data Index: 3321019 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1589. Min Range: -5.1589
Max Act: 4.9714. Min Act: -0.1700
Data Index: 1571622 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1589. Min Range: -5.1589
Max Act: 4.9402. Min Act: -0.1700
Data Index: 331052 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1589. Min Range: -5.1589
Max Act: 4.9089. Min Act: -0.1700
Data Index: 8038859 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1589. Min Range: -5.1589
Max Act: 4.9089. Min Act: -0.1700
Data Index: 2687721 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1589. Min Range: -5.1589
Max Act: 4.9089. Min Act: -0.1700
Data Index: 2984275 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1589. Min Range: -5.1589
Max Act: 4.9089. Min Act: -0.1700
Data Index: 2980615 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19