Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 93 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.2759. Min Range: -2.2759
Max Act: 2.2759. Min Act: -0.1700
Data Index: 100059 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2759. Min Range: -2.2759
Max Act: 2.2759. Min Act: -0.1700
Data Index: 880910 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2759. Min Range: -2.2759
Max Act: 2.2429. Min Act: -0.1700
Data Index: 50796 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2759. Min Range: -2.2759
Max Act: 2.2429. Min Act: -0.1700
Data Index: 1355465 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2759. Min Range: -2.2759
Max Act: 2.2263. Min Act: -0.1700
Data Index: 347805 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2759. Min Range: -2.2759
Max Act: 2.2263. Min Act: -0.1700
Data Index: 1048842 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2759. Min Range: -2.2759
Max Act: 2.2263. Min Act: -0.1700
Data Index: 521809 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2759. Min Range: -2.2759
Max Act: 2.2098. Min Act: -0.1700
Data Index: 567186 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2759. Min Range: -2.2759
Max Act: 2.2263. Min Act: -0.1700
Data Index: 1211219 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2759. Min Range: -2.2759
Max Act: 2.2098. Min Act: -0.1700
Data Index: 996156 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2759. Min Range: -2.2759
Max Act: 2.2098. Min Act: -0.1700
Data Index: 492914 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2759. Min Range: -2.2759
Max Act: 2.2098. Min Act: -0.1700
Data Index: 43575 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2759. Min Range: -2.2759
Max Act: 2.2098. Min Act: -0.1700
Data Index: 111919 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2759. Min Range: -2.2759
Max Act: 2.1932. Min Act: -0.1700
Data Index: 306074 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2759. Min Range: -2.2759
Max Act: 2.1932. Min Act: -0.1700
Data Index: 424728 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2759. Min Range: -2.2759
Max Act: 2.1932. Min Act: -0.1700
Data Index: 417487 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2759. Min Range: -2.2759
Max Act: 2.1932. Min Act: -0.1700
Data Index: 218645 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2759. Min Range: -2.2759
Max Act: 2.1932. Min Act: -0.1700
Data Index: 985366 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2759. Min Range: -2.2759
Max Act: 2.1932. Min Act: -0.1700
Data Index: 888775 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2759. Min Range: -2.2759
Max Act: 2.1766. Min Act: -0.1700
Data Index: 273670 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19