Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2029 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.4714. Min Range: -4.4714
Max Act: 4.4714. Min Act: -0.1700
Data Index: 239915 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4714. Min Range: -4.4714
Max Act: 4.4401. Min Act: -0.1700
Data Index: 930500 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4714. Min Range: -4.4714
Max Act: 4.4401. Min Act: -0.1700
Data Index: 1212432 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4714. Min Range: -4.4714
Max Act: 4.2839. Min Act: -0.1700
Data Index: 978546 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4714. Min Range: -4.4714
Max Act: 4.3464. Min Act: -0.1700
Data Index: 345337 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4714. Min Range: -4.4714
Max Act: 4.3151. Min Act: -0.1700
Data Index: 910831 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4714. Min Range: -4.4714
Max Act: 4.2839. Min Act: -0.1700
Data Index: 1169883 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4714. Min Range: -4.4714
Max Act: 4.1588. Min Act: -0.1700
Data Index: 913538 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4714. Min Range: -4.4714
Max Act: 4.1901. Min Act: -0.1700
Data Index: 550800 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4714. Min Range: -4.4714
Max Act: 4.1901. Min Act: -0.1700
Data Index: 859731 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4714. Min Range: -4.4714
Max Act: 4.1588. Min Act: -0.1700
Data Index: 967770 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4714. Min Range: -4.4714
Max Act: 4.1588. Min Act: -0.1700
Data Index: 621057 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4714. Min Range: -4.4714
Max Act: 4.2213. Min Act: -0.1700
Data Index: 117430 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4714. Min Range: -4.4714
Max Act: 4.1276. Min Act: -0.1700
Data Index: 782753 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4714. Min Range: -4.4714
Max Act: 4.1276. Min Act: -0.1700
Data Index: 166461 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4714. Min Range: -4.4714
Max Act: 4.0963. Min Act: -0.1700
Data Index: 1246218 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4714. Min Range: -4.4714
Max Act: 4.0963. Min Act: -0.1700
Data Index: 1083851 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4714. Min Range: -4.4714
Max Act: 4.0963. Min Act: -0.1700
Data Index: 719711 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4714. Min Range: -4.4714
Max Act: 4.0650. Min Act: -0.1700
Data Index: 861564 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4714. Min Range: -4.4714
Max Act: 4.0338. Min Act: -0.1700
Data Index: 887762 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19