Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 64 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.2184. Min Range: -3.2184
Max Act: 3.2184. Min Act: -0.1700
Data Index: 1432739 (Python Code)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2184. Min Range: -3.2184
Max Act: 3.1869. Min Act: -0.1700
Data Index: 1570641 (Python Code)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2184. Min Range: -3.2184
Max Act: 3.0924. Min Act: -0.1700
Data Index: 1469015 (Python Code)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2184. Min Range: -3.2184
Max Act: 3.0924. Min Act: -0.1700
Data Index: 1645509 (Python Code)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2184. Min Range: -3.2184
Max Act: 3.0924. Min Act: -0.1700
Data Index: 1592323 (Python Code)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2184. Min Range: -3.2184
Max Act: 3.0924. Min Act: -0.1700
Data Index: 1619437 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2184. Min Range: -3.2184
Max Act: 3.0924. Min Act: -0.1700
Data Index: 1374038 (Python Code)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2184. Min Range: -3.2184
Max Act: 3.0609. Min Act: -0.1700
Data Index: 1482074 (Python Code)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2184. Min Range: -3.2184
Max Act: 3.0451. Min Act: -0.1700
Data Index: 1607261 (Python Code)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2184. Min Range: -3.2184
Max Act: 3.0451. Min Act: -0.1700
Data Index: 1384780 (Python Code)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2184. Min Range: -3.2184
Max Act: 3.0451. Min Act: -0.1700
Data Index: 1439690 (Python Code)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2184. Min Range: -3.2184
Max Act: 3.0451. Min Act: -0.1700
Data Index: 1646165 (Python Code)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2184. Min Range: -3.2184
Max Act: 3.0293. Min Act: -0.1700
Data Index: 1625926 (Python Code)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2184. Min Range: -3.2184
Max Act: 2.9977. Min Act: -0.1700
Data Index: 1588760 (Python Code)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2184. Min Range: -3.2184
Max Act: 3.0293. Min Act: -0.1700
Data Index: 1368370 (Python Code)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2184. Min Range: -3.2184
Max Act: 2.9977. Min Act: -0.1700
Data Index: 1493874 (Python Code)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2184. Min Range: -3.2184
Max Act: 2.9977. Min Act: -0.1700
Data Index: 1427217 (Python Code)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2184. Min Range: -3.2184
Max Act: 2.9660. Min Act: -0.1700
Data Index: 1463562 (Python Code)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2184. Min Range: -3.2184
Max Act: 2.9819. Min Act: -0.1700
Data Index: 1650239 (Python Code)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2184. Min Range: -3.2184
Max Act: 2.9502. Min Act: -0.1700
Data Index: 1467981 (Python Code)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19