Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1227 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.3265. Min Range: -6.3265
Max Act: 6.3265. Min Act: -0.1700
Data Index: 387798 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3265. Min Range: -6.3265
Max Act: 6.3265. Min Act: -0.1700
Data Index: 956244 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3265. Min Range: -6.3265
Max Act: 6.3265. Min Act: -0.1700
Data Index: 1191743 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3265. Min Range: -6.3265
Max Act: 6.2640. Min Act: -0.1700
Data Index: 278659 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3265. Min Range: -6.3265
Max Act: 6.2952. Min Act: -0.1700
Data Index: 392059 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3265. Min Range: -6.3265
Max Act: 6.2327. Min Act: -0.1700
Data Index: 239555 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3265. Min Range: -6.3265
Max Act: 6.2640. Min Act: -0.1700
Data Index: 594778 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3265. Min Range: -6.3265
Max Act: 6.2640. Min Act: -0.1700
Data Index: 1251390 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3265. Min Range: -6.3265
Max Act: 6.2015. Min Act: -0.1700
Data Index: 240835 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3265. Min Range: -6.3265
Max Act: 6.2327. Min Act: -0.1700
Data Index: 906524 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3265. Min Range: -6.3265
Max Act: 6.2640. Min Act: -0.1700
Data Index: 1162335 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3265. Min Range: -6.3265
Max Act: 6.1702. Min Act: -0.1700
Data Index: 1156296 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3265. Min Range: -6.3265
Max Act: 6.2015. Min Act: -0.1700
Data Index: 563412 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3265. Min Range: -6.3265
Max Act: 6.2015. Min Act: -0.1700
Data Index: 197215 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3265. Min Range: -6.3265
Max Act: 6.2015. Min Act: -0.1700
Data Index: 419203 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3265. Min Range: -6.3265
Max Act: 6.2015. Min Act: -0.1700
Data Index: 386958 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3265. Min Range: -6.3265
Max Act: 6.2015. Min Act: -0.1700
Data Index: 1169872 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3265. Min Range: -6.3265
Max Act: 6.2015. Min Act: -0.1700
Data Index: 1173714 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3265. Min Range: -6.3265
Max Act: 6.1702. Min Act: -0.1700
Data Index: 245748 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3265. Min Range: -6.3265
Max Act: 6.1702. Min Act: -0.1700
Data Index: 319830 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19