Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 173 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1807. Min Range: -4.1807
Max Act: 4.1807. Min Act: -0.1700
Data Index: 1035189 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1807. Min Range: -4.1807
Max Act: 4.1494. Min Act: -0.1700
Data Index: 52223 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1807. Min Range: -4.1807
Max Act: 4.1182. Min Act: -0.1700
Data Index: 842159 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1807. Min Range: -4.1807
Max Act: 4.0869. Min Act: -0.1700
Data Index: 259593 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1807. Min Range: -4.1807
Max Act: 4.0244. Min Act: -0.1700
Data Index: 1311683 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1807. Min Range: -4.1807
Max Act: 4.0557. Min Act: -0.1700
Data Index: 20083 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1807. Min Range: -4.1807
Max Act: 4.0244. Min Act: -0.1700
Data Index: 964025 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1807. Min Range: -4.1807
Max Act: 4.0244. Min Act: -0.1700
Data Index: 1166529 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1807. Min Range: -4.1807
Max Act: 4.0244. Min Act: -0.1700
Data Index: 357865 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1807. Min Range: -4.1807
Max Act: 4.0557. Min Act: -0.1700
Data Index: 1237717 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1807. Min Range: -4.1807
Max Act: 4.0557. Min Act: -0.1700
Data Index: 1304299 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1807. Min Range: -4.1807
Max Act: 3.9619. Min Act: -0.1700
Data Index: 540083 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1807. Min Range: -4.1807
Max Act: 3.9931. Min Act: -0.1700
Data Index: 189221 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1807. Min Range: -4.1807
Max Act: 3.9931. Min Act: -0.1700
Data Index: 696937 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1807. Min Range: -4.1807
Max Act: 4.0244. Min Act: -0.1700
Data Index: 60784 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1807. Min Range: -4.1807
Max Act: 3.9931. Min Act: -0.1700
Data Index: 69373 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1807. Min Range: -4.1807
Max Act: 3.9619. Min Act: -0.1700
Data Index: 924268 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1807. Min Range: -4.1807
Max Act: 3.9619. Min Act: -0.1700
Data Index: 21904 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1807. Min Range: -4.1807
Max Act: 3.9619. Min Act: -0.1700
Data Index: 613943 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1807. Min Range: -4.1807
Max Act: 3.8993. Min Act: -0.1700
Data Index: 330358 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19