Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 193 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.0929. Min Range: -5.0929
Max Act: 5.0929. Min Act: -0.1700
Data Index: 352923 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0929. Min Range: -5.0929
Max Act: 4.8429. Min Act: -0.1700
Data Index: 49060 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0929. Min Range: -5.0929
Max Act: 4.8429. Min Act: -0.1700
Data Index: 81449 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0929. Min Range: -5.0929
Max Act: 4.8116. Min Act: -0.1700
Data Index: 596556 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0929. Min Range: -5.0929
Max Act: 4.7179. Min Act: -0.1700
Data Index: 1372189 (Python Code)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0929. Min Range: -5.0929
Max Act: 4.7179. Min Act: -0.1700
Data Index: 1606092 (Python Code)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0929. Min Range: -5.0929
Max Act: 4.7179. Min Act: -0.1700
Data Index: 922607 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0929. Min Range: -5.0929
Max Act: 4.6241. Min Act: -0.1700
Data Index: 385716 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0929. Min Range: -5.0929
Max Act: 4.6866. Min Act: -0.1700
Data Index: 991366 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0929. Min Range: -5.0929
Max Act: 4.6241. Min Act: -0.1700
Data Index: 205444 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0929. Min Range: -5.0929
Max Act: 4.6554. Min Act: -0.1700
Data Index: 1585786 (Python Code)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0929. Min Range: -5.0929
Max Act: 4.6866. Min Act: -0.1700
Data Index: 1615602 (Python Code)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0929. Min Range: -5.0929
Max Act: 4.5929. Min Act: -0.1700
Data Index: 1465435 (Python Code)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0929. Min Range: -5.0929
Max Act: 4.5304. Min Act: -0.1700
Data Index: 1085889 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0929. Min Range: -5.0929
Max Act: 4.5929. Min Act: -0.1700
Data Index: 297792 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0929. Min Range: -5.0929
Max Act: 4.6554. Min Act: -0.1700
Data Index: 976296 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0929. Min Range: -5.0929
Max Act: 4.6241. Min Act: -0.1700
Data Index: 352725 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0929. Min Range: -5.0929
Max Act: 4.5616. Min Act: -0.1700
Data Index: 1572664 (Python Code)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0929. Min Range: -5.0929
Max Act: 4.6241. Min Act: -0.1700
Data Index: 1656610 (Python Code)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0929. Min Range: -5.0929
Max Act: 4.6241. Min Act: -0.1700
Data Index: 1013729 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19