Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 286 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0729. Min Range: -4.0729
Max Act: 4.0729. Min Act: -0.1700
Data Index: 185552 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0729. Min Range: -4.0729
Max Act: 4.0416. Min Act: -0.1700
Data Index: 1036829 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.8540. Min Act: -0.1700
Data Index: 299536 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.9165. Min Act: -0.1700
Data Index: 935721 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.7914. Min Act: -0.1700
Data Index: 1158972 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.7914. Min Act: -0.1700
Data Index: 202820 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.8540. Min Act: -0.1700
Data Index: 332587 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.7601. Min Act: -0.1700
Data Index: 732949 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.7601. Min Act: -0.1700
Data Index: 118746 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.7601. Min Act: -0.1700
Data Index: 1181583 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.7289. Min Act: -0.1700
Data Index: 1246350 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.6976. Min Act: -0.1700
Data Index: 290131 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.7289. Min Act: -0.1700
Data Index: 492526 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.7601. Min Act: -0.1700
Data Index: 339401 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.6037. Min Act: -0.1700
Data Index: 675824 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.7289. Min Act: -0.1700
Data Index: 1116629 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.7601. Min Act: -0.1700
Data Index: 59794 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.6976. Min Act: -0.1700
Data Index: 234610 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.6663. Min Act: -0.1700
Data Index: 304377 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0729. Min Range: -4.0729
Max Act: 3.6976. Min Act: -0.1700
Data Index: 113435 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19