Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1988 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.8985. Min Range: -4.8985
Max Act: 4.8985. Min Act: -0.1700
Data Index: 1516359 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8985. Min Range: -4.8985
Max Act: 4.8048. Min Act: -0.1700
Data Index: 1655164 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8985. Min Range: -4.8985
Max Act: 4.6173. Min Act: -0.1700
Data Index: 1401162 (Python Code)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8985. Min Range: -4.8985
Max Act: 4.6173. Min Act: -0.1700
Data Index: 1605087 (Python Code)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8985. Min Range: -4.8985
Max Act: 4.5860. Min Act: -0.1700
Data Index: 1464962 (Python Code)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8985. Min Range: -4.8985
Max Act: 4.5860. Min Act: -0.1700
Data Index: 1466484 (Python Code)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8985. Min Range: -4.8985
Max Act: 4.5860. Min Act: -0.1700
Data Index: 1375318 (Python Code)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8985. Min Range: -4.8985
Max Act: 4.5860. Min Act: -0.1700
Data Index: 1423581 (Python Code)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8985. Min Range: -4.8985
Max Act: 4.5548. Min Act: -0.1700
Data Index: 1439498 (Python Code)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8985. Min Range: -4.8985
Max Act: 4.5860. Min Act: -0.1700
Data Index: 1363076 (Python Code)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8985. Min Range: -4.8985
Max Act: 4.5235. Min Act: -0.1700
Data Index: 1444992 (Python Code)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8985. Min Range: -4.8985
Max Act: 4.5235. Min Act: -0.1700
Data Index: 1656477 (Python Code)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8985. Min Range: -4.8985
Max Act: 4.5235. Min Act: -0.1700
Data Index: 1406410 (Python Code)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8985. Min Range: -4.8985
Max Act: 4.5235. Min Act: -0.1700
Data Index: 1564564 (Python Code)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8985. Min Range: -4.8985
Max Act: 4.5235. Min Act: -0.1700
Data Index: 1595592 (Python Code)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8985. Min Range: -4.8985
Max Act: 4.5235. Min Act: -0.1700
Data Index: 606278 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8985. Min Range: -4.8985
Max Act: 4.4923. Min Act: -0.1700
Data Index: 1602980 (Python Code)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8985. Min Range: -4.8985
Max Act: 4.4923. Min Act: -0.1700
Data Index: 1470342 (Python Code)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8985. Min Range: -4.8985
Max Act: 4.4923. Min Act: -0.1700
Data Index: 1642589 (Python Code)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8985. Min Range: -4.8985
Max Act: 4.4923. Min Act: -0.1700
Data Index: 1431732 (Python Code)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19