Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 452 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8076. Min Range: -2.8076
Max Act: 2.8076. Min Act: -0.1700
Data Index: 1409183 (Python Code)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8076. Min Range: -2.8076
Max Act: 2.8076. Min Act: -0.1700
Data Index: 1278293 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8076. Min Range: -2.8076
Max Act: 2.8076. Min Act: -0.1700
Data Index: 1531842 (Python Code)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8076. Min Range: -2.8076
Max Act: 2.8076. Min Act: -0.1700
Data Index: 1409126 (Python Code)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8076. Min Range: -2.8076
Max Act: 2.7917. Min Act: -0.1700
Data Index: 1550983 (Python Code)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8076. Min Range: -2.8076
Max Act: 2.7757. Min Act: -0.1700
Data Index: 1497356 (Python Code)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8076. Min Range: -2.8076
Max Act: 2.7757. Min Act: -0.1700
Data Index: 1383859 (Python Code)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8076. Min Range: -2.8076
Max Act: 2.7757. Min Act: -0.1700
Data Index: 1397307 (Python Code)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8076. Min Range: -2.8076
Max Act: 2.7757. Min Act: -0.1700
Data Index: 1461333 (Python Code)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8076. Min Range: -2.8076
Max Act: 2.7917. Min Act: -0.1700
Data Index: 1497791 (Python Code)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8076. Min Range: -2.8076
Max Act: 2.7757. Min Act: -0.1700
Data Index: 1482307 (Python Code)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8076. Min Range: -2.8076
Max Act: 2.7598. Min Act: -0.1700
Data Index: 1634809 (Python Code)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8076. Min Range: -2.8076
Max Act: 2.7438. Min Act: -0.1700
Data Index: 929854 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8076. Min Range: -2.8076
Max Act: 2.7598. Min Act: -0.1700
Data Index: 1533711 (Python Code)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8076. Min Range: -2.8076
Max Act: 2.7438. Min Act: -0.1700
Data Index: 1408244 (Python Code)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8076. Min Range: -2.8076
Max Act: 2.7438. Min Act: -0.1700
Data Index: 1526720 (Python Code)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8076. Min Range: -2.8076
Max Act: 2.7438. Min Act: -0.1700
Data Index: 1382645 (Python Code)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8076. Min Range: -2.8076
Max Act: 2.7438. Min Act: -0.1700
Data Index: 1363125 (Python Code)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8076. Min Range: -2.8076
Max Act: 2.7278. Min Act: -0.1700
Data Index: 1446955 (Python Code)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8076. Min Range: -2.8076
Max Act: 2.7438. Min Act: -0.1700
Data Index: 1368335 (Python Code)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19