Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 108 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8667. Min Range: -2.8667
Max Act: 2.8667. Min Act: -0.1700
Data Index: 522738 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8667. Min Range: -2.8667
Max Act: 2.8349. Min Act: -0.1700
Data Index: 19685 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8667. Min Range: -2.8667
Max Act: 2.8349. Min Act: -0.1700
Data Index: 1094816 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8667. Min Range: -2.8667
Max Act: 2.8031. Min Act: -0.1700
Data Index: 427365 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8667. Min Range: -2.8667
Max Act: 2.7872. Min Act: -0.1700
Data Index: 898386 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8667. Min Range: -2.8667
Max Act: 2.7553. Min Act: -0.1700
Data Index: 1026057 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8667. Min Range: -2.8667
Max Act: 2.7712. Min Act: -0.1700
Data Index: 250687 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8667. Min Range: -2.8667
Max Act: 2.7393. Min Act: -0.1700
Data Index: 346748 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8667. Min Range: -2.8667
Max Act: 2.7393. Min Act: -0.1700
Data Index: 1096585 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8667. Min Range: -2.8667
Max Act: 2.7233. Min Act: -0.1700
Data Index: 531343 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8667. Min Range: -2.8667
Max Act: 2.7073. Min Act: -0.1700
Data Index: 1310444 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8667. Min Range: -2.8667
Max Act: 2.7073. Min Act: -0.1700
Data Index: 478625 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8667. Min Range: -2.8667
Max Act: 2.7073. Min Act: -0.1700
Data Index: 489437 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8667. Min Range: -2.8667
Max Act: 2.7233. Min Act: -0.1700
Data Index: 10691 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8667. Min Range: -2.8667
Max Act: 2.6913. Min Act: -0.1700
Data Index: 665823 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8667. Min Range: -2.8667
Max Act: 2.6753. Min Act: -0.1700
Data Index: 1456066 (Python Code)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8667. Min Range: -2.8667
Max Act: 2.6753. Min Act: -0.1700
Data Index: 524532 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8667. Min Range: -2.8667
Max Act: 2.6593. Min Act: -0.1700
Data Index: 28126 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8667. Min Range: -2.8667
Max Act: 2.6913. Min Act: -0.1700
Data Index: 136403 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8667. Min Range: -2.8667
Max Act: 2.6753. Min Act: -0.1700
Data Index: 339026 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19