Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 526 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7045. Min Range: -2.7045
Max Act: 2.7045. Min Act: -0.1700
Data Index: 361529 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7045. Min Range: -2.7045
Max Act: 2.5115. Min Act: -0.1700
Data Index: 85280 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7045. Min Range: -2.7045
Max Act: 2.5115. Min Act: -0.1700
Data Index: 1555895 (Python Code)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7045. Min Range: -2.7045
Max Act: 2.4953. Min Act: -0.1700
Data Index: 1394219 (Python Code)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7045. Min Range: -2.7045
Max Act: 2.4629. Min Act: -0.1700
Data Index: 1252831 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7045. Min Range: -2.7045
Max Act: 2.4466. Min Act: -0.1700
Data Index: 408817 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7045. Min Range: -2.7045
Max Act: 2.4304. Min Act: -0.1700
Data Index: 1462688 (Python Code)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7045. Min Range: -2.7045
Max Act: 2.4466. Min Act: -0.1700
Data Index: 1654243 (Python Code)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7045. Min Range: -2.7045
Max Act: 2.4304. Min Act: -0.1700
Data Index: 104824 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7045. Min Range: -2.7045
Max Act: 2.4466. Min Act: -0.1700
Data Index: 616013 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7045. Min Range: -2.7045
Max Act: 2.4304. Min Act: -0.1700
Data Index: 39018 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7045. Min Range: -2.7045
Max Act: 2.4304. Min Act: -0.1700
Data Index: 207658 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7045. Min Range: -2.7045
Max Act: 2.4141. Min Act: -0.1700
Data Index: 28894 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7045. Min Range: -2.7045
Max Act: 2.4141. Min Act: -0.1700
Data Index: 1242668 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7045. Min Range: -2.7045
Max Act: 2.4141. Min Act: -0.1700
Data Index: 223949 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7045. Min Range: -2.7045
Max Act: 2.3978. Min Act: -0.1700
Data Index: 887216 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7045. Min Range: -2.7045
Max Act: 2.4141. Min Act: -0.1700
Data Index: 98621 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7045. Min Range: -2.7045
Max Act: 2.3978. Min Act: -0.1700
Data Index: 1404997 (Python Code)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7045. Min Range: -2.7045
Max Act: 2.3978. Min Act: -0.1700
Data Index: 412846 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7045. Min Range: -2.7045
Max Act: 2.3978. Min Act: -0.1700
Data Index: 1298909 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19