Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1844 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7912. Min Range: -2.7912
Max Act: 2.7752. Min Act: -0.1700
Data Index: 1475490 (Python Code)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7912. Min Range: -2.7912
Max Act: 2.7912. Min Act: -0.1700
Data Index: 1566852 (Python Code)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7912. Min Range: -2.7912
Max Act: 2.6793. Min Act: -0.1700
Data Index: 1649627 (Python Code)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7912. Min Range: -2.7912
Max Act: 2.6151. Min Act: -0.1700
Data Index: 1592748 (Python Code)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7912. Min Range: -2.7912
Max Act: 2.6312. Min Act: -0.1700
Data Index: 1600478 (Python Code)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7912. Min Range: -2.7912
Max Act: 2.6312. Min Act: -0.1700
Data Index: 1495972 (Python Code)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7912. Min Range: -2.7912
Max Act: 2.6151. Min Act: -0.1700
Data Index: 1461841 (Python Code)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7912. Min Range: -2.7912
Max Act: 2.5829. Min Act: -0.1700
Data Index: 177107 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7912. Min Range: -2.7912
Max Act: 2.5507. Min Act: -0.1700
Data Index: 1632732 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7912. Min Range: -2.7912
Max Act: 2.5345. Min Act: -0.1700
Data Index: 1368513 (Python Code)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7912. Min Range: -2.7912
Max Act: 2.5507. Min Act: -0.1700
Data Index: 1622223 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7912. Min Range: -2.7912
Max Act: 2.5345. Min Act: -0.1700
Data Index: 1638914 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7912. Min Range: -2.7912
Max Act: 2.5022. Min Act: -0.1699
Data Index: 1417665 (Python Code)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7912. Min Range: -2.7912
Max Act: 2.5022. Min Act: -0.1700
Data Index: 154111 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7912. Min Range: -2.7912
Max Act: 2.4860. Min Act: -0.1700
Data Index: 1393791 (Python Code)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7912. Min Range: -2.7912
Max Act: 2.4698. Min Act: -0.1700
Data Index: 809758 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7912. Min Range: -2.7912
Max Act: 2.4860. Min Act: -0.1700
Data Index: 811731 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7912. Min Range: -2.7912
Max Act: 2.5022. Min Act: -0.1700
Data Index: 393044 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7912. Min Range: -2.7912
Max Act: 2.4860. Min Act: -0.1700
Data Index: 686343 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7912. Min Range: -2.7912
Max Act: 2.4698. Min Act: -0.1700
Data Index: 1568011 (Python Code)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19