Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1513 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9554. Min Range: -4.9554
Max Act: 4.9554. Min Act: -0.1700
Data Index: 1261456 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9554. Min Range: -4.9554
Max Act: 4.9242. Min Act: -0.1700
Data Index: 887577 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9554. Min Range: -4.9554
Max Act: 4.9554. Min Act: -0.1700
Data Index: 407568 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9554. Min Range: -4.9554
Max Act: 4.8929. Min Act: -0.1700
Data Index: 1063102 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9554. Min Range: -4.9554
Max Act: 4.8929. Min Act: -0.1700
Data Index: 787683 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9554. Min Range: -4.9554
Max Act: 4.8929. Min Act: -0.1700
Data Index: 1057692 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9554. Min Range: -4.9554
Max Act: 4.8304. Min Act: -0.1700
Data Index: 918661 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9554. Min Range: -4.9554
Max Act: 4.8304. Min Act: -0.1699
Data Index: 313039 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9554. Min Range: -4.9554
Max Act: 4.7679. Min Act: -0.1700
Data Index: 1269154 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9554. Min Range: -4.9554
Max Act: 4.7367. Min Act: -0.1700
Data Index: 27518 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9554. Min Range: -4.9554
Max Act: 4.6742. Min Act: -0.1700
Data Index: 126659 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9554. Min Range: -4.9554
Max Act: 4.7054. Min Act: -0.1700
Data Index: 913859 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9554. Min Range: -4.9554
Max Act: 4.7054. Min Act: -0.1700
Data Index: 417888 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9554. Min Range: -4.9554
Max Act: 4.6742. Min Act: -0.1700
Data Index: 954870 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9554. Min Range: -4.9554
Max Act: 4.7367. Min Act: -0.1700
Data Index: 470393 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9554. Min Range: -4.9554
Max Act: 4.6742. Min Act: -0.1700
Data Index: 481174 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9554. Min Range: -4.9554
Max Act: 4.7054. Min Act: -0.1700
Data Index: 1102918 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9554. Min Range: -4.9554
Max Act: 4.6742. Min Act: -0.1700
Data Index: 905016 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9554. Min Range: -4.9554
Max Act: 4.6429. Min Act: -0.1700
Data Index: 1080844 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9554. Min Range: -4.9554
Max Act: 4.7054. Min Act: -0.1700
Data Index: 994648 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19