Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1134 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9563. Min Range: -2.9563
Max Act: 2.9563. Min Act: -0.1700
Data Index: 1614218 (Python Code)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9563. Min Range: -2.9563
Max Act: 2.8929. Min Act: -0.1700
Data Index: 1400181 (Python Code)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9563. Min Range: -2.9563
Max Act: 2.8771. Min Act: -0.1700
Data Index: 827841 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9563. Min Range: -2.9563
Max Act: 2.8929. Min Act: -0.1700
Data Index: 1616520 (Python Code)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9563. Min Range: -2.9563
Max Act: 2.8771. Min Act: -0.1700
Data Index: 1409635 (Python Code)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9563. Min Range: -2.9563
Max Act: 2.8771. Min Act: -0.1700
Data Index: 1544362 (Python Code)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9563. Min Range: -2.9563
Max Act: 2.8612. Min Act: -0.1700
Data Index: 1554637 (Python Code)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9563. Min Range: -2.9563
Max Act: 2.8771. Min Act: -0.1700
Data Index: 701087 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9563. Min Range: -2.9563
Max Act: 2.8771. Min Act: -0.1700
Data Index: 1428798 (Python Code)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9563. Min Range: -2.9563
Max Act: 2.8771. Min Act: -0.1700
Data Index: 1615698 (Python Code)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9563. Min Range: -2.9563
Max Act: 2.8771. Min Act: -0.1700
Data Index: 1467252 (Python Code)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9563. Min Range: -2.9563
Max Act: 2.8771. Min Act: -0.1700
Data Index: 1607260 (Python Code)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9563. Min Range: -2.9563
Max Act: 2.8453. Min Act: -0.1700
Data Index: 580002 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9563. Min Range: -2.9563
Max Act: 2.8453. Min Act: -0.1700
Data Index: 1500293 (Python Code)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9563. Min Range: -2.9563
Max Act: 2.8453. Min Act: -0.1700
Data Index: 1334863 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9563. Min Range: -2.9563
Max Act: 2.8453. Min Act: -0.1700
Data Index: 213640 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9563. Min Range: -2.9563
Max Act: 2.7976. Min Act: -0.1700
Data Index: 83715 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9563. Min Range: -2.9563
Max Act: 2.8135. Min Act: -0.1700
Data Index: 709054 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9563. Min Range: -2.9563
Max Act: 2.7976. Min Act: -0.1700
Data Index: 1091522 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9563. Min Range: -2.9563
Max Act: 2.7976. Min Act: -0.1700
Data Index: 1062338 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19