Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 22 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 6.5733. Min Range: -6.5733
Max Act: 6.5733. Min Act: -0.1700
Data Index: 1372948 (Python Code)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5733. Min Range: -6.5733
Max Act: 6.4483. Min Act: -0.1700
Data Index: 1493720 (Python Code)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5733. Min Range: -6.5733
Max Act: 6.2608. Min Act: -0.1700
Data Index: 1532776 (Python Code)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5733. Min Range: -6.5733
Max Act: 6.2608. Min Act: -0.1700
Data Index: 1605664 (Python Code)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5733. Min Range: -6.5733
Max Act: 6.2921. Min Act: -0.1700
Data Index: 1558378 (Python Code)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5733. Min Range: -6.5733
Max Act: 6.2608. Min Act: -0.1700
Data Index: 1496730 (Python Code)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5733. Min Range: -6.5733
Max Act: 6.2921. Min Act: -0.1700
Data Index: 1618062 (Python Code)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5733. Min Range: -6.5733
Max Act: 6.1983. Min Act: -0.1700
Data Index: 1506383 (Python Code)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5733. Min Range: -6.5733
Max Act: 6.1358. Min Act: -0.1700
Data Index: 1369532 (Python Code)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5733. Min Range: -6.5733
Max Act: 6.0733. Min Act: -0.1700
Data Index: 1381280 (Python Code)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5733. Min Range: -6.5733
Max Act: 6.1046. Min Act: -0.1700
Data Index: 1566045 (Python Code)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5733. Min Range: -6.5733
Max Act: 6.0421. Min Act: -0.1700
Data Index: 1561167 (Python Code)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5733. Min Range: -6.5733
Max Act: 6.1046. Min Act: -0.1700
Data Index: 1508522 (Python Code)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5733. Min Range: -6.5733
Max Act: 6.0421. Min Act: -0.1700
Data Index: 1418064 (Python Code)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5733. Min Range: -6.5733
Max Act: 6.1671. Min Act: -0.1700
Data Index: 1655855 (Python Code)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5733. Min Range: -6.5733
Max Act: 6.0421. Min Act: -0.1700
Data Index: 1529055 (Python Code)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5733. Min Range: -6.5733
Max Act: 5.9796. Min Act: -0.1700
Data Index: 1395398 (Python Code)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5733. Min Range: -6.5733
Max Act: 5.9796. Min Act: -0.1700
Data Index: 1615291 (Python Code)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5733. Min Range: -6.5733
Max Act: 6.0108. Min Act: -0.1700
Data Index: 1642249 (Python Code)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5733. Min Range: -6.5733
Max Act: 5.9796. Min Act: -0.1700
Data Index: 1640297 (Python Code)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19