Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2025 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.1843. Min Range: -4.1843
Max Act: 4.1843. Min Act: -0.1700
Data Index: 616235 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1843. Min Range: -4.1843
Max Act: 4.1062. Min Act: -0.1700
Data Index: 1655764 (Python Code)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1843. Min Range: -4.1843
Max Act: 4.1062. Min Act: -0.1700
Data Index: 36434 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1843. Min Range: -4.1843
Max Act: 4.0436. Min Act: -0.1700
Data Index: 1537047 (Python Code)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1843. Min Range: -4.1843
Max Act: 4.0124. Min Act: -0.1700
Data Index: 1577510 (Python Code)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1843. Min Range: -4.1843
Max Act: 4.0436. Min Act: -0.1700
Data Index: 1370552 (Python Code)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1843. Min Range: -4.1843
Max Act: 4.0436. Min Act: -0.1700
Data Index: 1637487 (Python Code)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1843. Min Range: -4.1843
Max Act: 4.0280. Min Act: -0.1700
Data Index: 1369863 (Python Code)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1843. Min Range: -4.1843
Max Act: 4.0593. Min Act: -0.1700
Data Index: 1471874 (Python Code)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1843. Min Range: -4.1843
Max Act: 4.0436. Min Act: -0.1700
Data Index: 492347 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1843. Min Range: -4.1843
Max Act: 4.0280. Min Act: -0.1700
Data Index: 1419309 (Python Code)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1843. Min Range: -4.1843
Max Act: 4.0593. Min Act: -0.1700
Data Index: 1586803 (Python Code)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1843. Min Range: -4.1843
Max Act: 4.0280. Min Act: -0.1700
Data Index: 1521355 (Python Code)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1843. Min Range: -4.1843
Max Act: 4.0593. Min Act: -0.1700
Data Index: 1465165 (Python Code)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1843. Min Range: -4.1843
Max Act: 4.0124. Min Act: -0.1700
Data Index: 1365837 (Python Code)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1843. Min Range: -4.1843
Max Act: 4.0124. Min Act: -0.1700
Data Index: 1465675 (Python Code)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1843. Min Range: -4.1843
Max Act: 3.9967. Min Act: -0.1700
Data Index: 1367218 (Python Code)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1843. Min Range: -4.1843
Max Act: 4.0280. Min Act: -0.1700
Data Index: 1602227 (Python Code)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1843. Min Range: -4.1843
Max Act: 4.0124. Min Act: -0.1700
Data Index: 945145 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1843. Min Range: -4.1843
Max Act: 4.0436. Min Act: -0.1700
Data Index: 666896 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19