Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2016 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9784. Min Range: -2.9784
Max Act: 2.9784. Min Act: -0.1700
Data Index: 951851 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9784. Min Range: -2.9784
Max Act: 2.9467. Min Act: -0.1700
Data Index: 170579 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9784. Min Range: -2.9784
Max Act: 2.8992. Min Act: -0.1700
Data Index: 609642 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9784. Min Range: -2.9784
Max Act: 2.9309. Min Act: -0.1700
Data Index: 1306995 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9784. Min Range: -2.9784
Max Act: 2.8992. Min Act: -0.1700
Data Index: 884796 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9784. Min Range: -2.9784
Max Act: 2.8833. Min Act: -0.1700
Data Index: 1082889 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9784. Min Range: -2.9784
Max Act: 2.8833. Min Act: -0.1700
Data Index: 249149 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9784. Min Range: -2.9784
Max Act: 2.8833. Min Act: -0.1700
Data Index: 340942 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9784. Min Range: -2.9784
Max Act: 2.8674. Min Act: -0.1700
Data Index: 661484 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9784. Min Range: -2.9784
Max Act: 2.8992. Min Act: -0.1700
Data Index: 933876 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9784. Min Range: -2.9784
Max Act: 2.8992. Min Act: -0.1700
Data Index: 899194 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9784. Min Range: -2.9784
Max Act: 2.8674. Min Act: -0.1700
Data Index: 235912 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9784. Min Range: -2.9784
Max Act: 2.8833. Min Act: -0.1700
Data Index: 187636 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9784. Min Range: -2.9784
Max Act: 2.8674. Min Act: -0.1700
Data Index: 354291 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9784. Min Range: -2.9784
Max Act: 2.8515. Min Act: -0.1700
Data Index: 1250934 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9784. Min Range: -2.9784
Max Act: 2.8515. Min Act: -0.1700
Data Index: 240980 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9784. Min Range: -2.9784
Max Act: 2.8197. Min Act: -0.1700
Data Index: 1036734 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9784. Min Range: -2.9784
Max Act: 2.8356. Min Act: -0.1700
Data Index: 381550 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9784. Min Range: -2.9784
Max Act: 2.8356. Min Act: -0.1700
Data Index: 276796 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9784. Min Range: -2.9784
Max Act: 2.8197. Min Act: -0.1700
Data Index: 888495 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19