Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1456 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.4256. Min Range: -4.4256
Max Act: 4.3944. Min Act: -0.1700
Data Index: 889957 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4256. Min Range: -4.4256
Max Act: 4.4256. Min Act: -0.1700
Data Index: 91024 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4256. Min Range: -4.4256
Max Act: 4.3944. Min Act: -0.1700
Data Index: 1312692 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4256. Min Range: -4.4256
Max Act: 4.3631. Min Act: -0.1700
Data Index: 980929 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4256. Min Range: -4.4256
Max Act: 4.3631. Min Act: -0.1700
Data Index: 929985 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4256. Min Range: -4.4256
Max Act: 4.3006. Min Act: -0.1700
Data Index: 1309830 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4256. Min Range: -4.4256
Max Act: 4.3319. Min Act: -0.1700
Data Index: 465611 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4256. Min Range: -4.4256
Max Act: 4.3319. Min Act: -0.1700
Data Index: 232176 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4256. Min Range: -4.4256
Max Act: 4.2693. Min Act: -0.1700
Data Index: 1208581 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4256. Min Range: -4.4256
Max Act: 4.3006. Min Act: -0.1700
Data Index: 474798 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4256. Min Range: -4.4256
Max Act: 4.3006. Min Act: -0.1700
Data Index: 753388 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4256. Min Range: -4.4256
Max Act: 4.3006. Min Act: -0.1700
Data Index: 834359 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4256. Min Range: -4.4256
Max Act: 4.2693. Min Act: -0.1700
Data Index: 1301058 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4256. Min Range: -4.4256
Max Act: 4.2693. Min Act: -0.1700
Data Index: 186070 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4256. Min Range: -4.4256
Max Act: 4.3319. Min Act: -0.1700
Data Index: 345046 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4256. Min Range: -4.4256
Max Act: 4.2693. Min Act: -0.1700
Data Index: 604864 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4256. Min Range: -4.4256
Max Act: 4.2381. Min Act: -0.1700
Data Index: 634389 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4256. Min Range: -4.4256
Max Act: 4.2693. Min Act: -0.1700
Data Index: 651501 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4256. Min Range: -4.4256
Max Act: 4.2693. Min Act: -0.1700
Data Index: 959676 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4256. Min Range: -4.4256
Max Act: 4.2693. Min Act: -0.1700
Data Index: 732610 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19