Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2012 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.6737. Min Range: -4.6737
Max Act: 4.6737. Min Act: -0.1700
Data Index: 258678 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6737. Min Range: -4.6737
Max Act: 4.6425. Min Act: -0.1700
Data Index: 1271413 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6737. Min Range: -4.6737
Max Act: 4.5800. Min Act: -0.1700
Data Index: 394155 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6737. Min Range: -4.6737
Max Act: 4.6112. Min Act: -0.1700
Data Index: 539039 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6737. Min Range: -4.6737
Max Act: 4.6112. Min Act: -0.1700
Data Index: 151719 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6737. Min Range: -4.6737
Max Act: 4.5800. Min Act: -0.1700
Data Index: 621737 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6737. Min Range: -4.6737
Max Act: 4.5175. Min Act: -0.1700
Data Index: 346268 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6737. Min Range: -4.6737
Max Act: 4.5487. Min Act: -0.1700
Data Index: 1166274 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6737. Min Range: -4.6737
Max Act: 4.5800. Min Act: -0.1700
Data Index: 1318665 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6737. Min Range: -4.6737
Max Act: 4.5175. Min Act: -0.1700
Data Index: 498968 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6737. Min Range: -4.6737
Max Act: 4.5487. Min Act: -0.1700
Data Index: 312614 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6737. Min Range: -4.6737
Max Act: 4.4862. Min Act: -0.1700
Data Index: 453306 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6737. Min Range: -4.6737
Max Act: 4.5175. Min Act: -0.1700
Data Index: 1024464 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6737. Min Range: -4.6737
Max Act: 4.4862. Min Act: -0.1700
Data Index: 55625 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6737. Min Range: -4.6737
Max Act: 4.5175. Min Act: -0.1700
Data Index: 956975 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6737. Min Range: -4.6737
Max Act: 4.4862. Min Act: -0.1700
Data Index: 772422 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6737. Min Range: -4.6737
Max Act: 4.4550. Min Act: -0.1700
Data Index: 995976 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6737. Min Range: -4.6737
Max Act: 4.4237. Min Act: -0.1700
Data Index: 1007936 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6737. Min Range: -4.6737
Max Act: 4.4550. Min Act: -0.1700
Data Index: 727339 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6737. Min Range: -4.6737
Max Act: 4.4550. Min Act: -0.1700
Data Index: 426441 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19