Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 447 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.3564. Min Range: -4.3564
Max Act: 4.3564. Min Act: -0.1700
Data Index: 354515 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3564. Min Range: -4.3564
Max Act: 4.2627. Min Act: -0.1700
Data Index: 1379484 (Python Code)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3564. Min Range: -4.3564
Max Act: 4.2002. Min Act: -0.1700
Data Index: 381144 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3564. Min Range: -4.3564
Max Act: 4.2314. Min Act: -0.1700
Data Index: 931724 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3564. Min Range: -4.3564
Max Act: 4.2002. Min Act: -0.1700
Data Index: 443059 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3564. Min Range: -4.3564
Max Act: 4.2002. Min Act: -0.1700
Data Index: 1522827 (Python Code)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3564. Min Range: -4.3564
Max Act: 4.2314. Min Act: -0.1700
Data Index: 113670 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3564. Min Range: -4.3564
Max Act: 4.2002. Min Act: -0.1700
Data Index: 974611 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3564. Min Range: -4.3564
Max Act: 4.1689. Min Act: -0.1700
Data Index: 1633357 (Python Code)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3564. Min Range: -4.3564
Max Act: 4.1689. Min Act: -0.1700
Data Index: 1475216 (Python Code)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3564. Min Range: -4.3564
Max Act: 4.1689. Min Act: -0.1700
Data Index: 1554109 (Python Code)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3564. Min Range: -4.3564
Max Act: 4.1689. Min Act: -0.1700
Data Index: 807666 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3564. Min Range: -4.3564
Max Act: 4.1689. Min Act: -0.1700
Data Index: 354007 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3564. Min Range: -4.3564
Max Act: 4.1376. Min Act: -0.1700
Data Index: 247085 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3564. Min Range: -4.3564
Max Act: 4.1064. Min Act: -0.1700
Data Index: 1503713 (Python Code)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3564. Min Range: -4.3564
Max Act: 4.1064. Min Act: -0.1700
Data Index: 1506869 (Python Code)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3564. Min Range: -4.3564
Max Act: 4.1376. Min Act: -0.1700
Data Index: 1635771 (Python Code)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3564. Min Range: -4.3564
Max Act: 4.1689. Min Act: -0.1700
Data Index: 1493717 (Python Code)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3564. Min Range: -4.3564
Max Act: 4.1064. Min Act: -0.1700
Data Index: 1408094 (Python Code)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3564. Min Range: -4.3564
Max Act: 4.1689. Min Act: -0.1700
Data Index: 918035 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19