Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2046 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.0648. Min Range: -3.0648
Max Act: 3.0648. Min Act: -0.0001
Data Index: 1637239 (Python Code)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0648. Min Range: -3.0648
Max Act: 2.8372. Min Act: -0.0001
Data Index: 1646564 (Python Code)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0648. Min Range: -3.0648
Max Act: 2.9384. Min Act: -0.0001
Data Index: 1558817 (Python Code)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0648. Min Range: -3.0648
Max Act: 2.9228. Min Act: -0.0001
Data Index: 1202523 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0648. Min Range: -3.0648
Max Act: 2.7673. Min Act: -0.0001
Data Index: 107156 (C4 (Web Text))
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0648. Min Range: -3.0648
Max Act: 2.8560. Min Act: -0.0001
Data Index: 386039 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0648. Min Range: -3.0648
Max Act: 2.8523. Min Act: -0.0001
Data Index: 1459023 (Python Code)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0648. Min Range: -3.0648
Max Act: 2.8306. Min Act: -0.0001
Data Index: 1480306 (Python Code)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0648. Min Range: -3.0648
Max Act: 2.8443. Min Act: -0.0001
Data Index: 1387311 (Python Code)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0648. Min Range: -3.0648
Max Act: 2.9717. Min Act: -0.0001
Data Index: 1574369 (Python Code)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0648. Min Range: -3.0648
Max Act: 2.8126. Min Act: -0.0001
Data Index: 1474481 (Python Code)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0648. Min Range: -3.0648
Max Act: 2.8253. Min Act: -0.0001
Data Index: 1392333 (Python Code)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0648. Min Range: -3.0648
Max Act: 2.9484. Min Act: -0.0001
Data Index: 1551144 (Python Code)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0648. Min Range: -3.0648
Max Act: 2.8000. Min Act: -0.0001
Data Index: 1466419 (Python Code)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0648. Min Range: -3.0648
Max Act: 2.9480. Min Act: -0.0001
Data Index: 1623398 (Python Code)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0648. Min Range: -3.0648
Max Act: 2.7989. Min Act: -0.0001
Data Index: 1586129 (Python Code)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0648. Min Range: -3.0648
Max Act: 2.6731. Min Act: -0.0001
Data Index: 1477549 (Python Code)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0648. Min Range: -3.0648
Max Act: 2.7987. Min Act: -0.0001
Data Index: 1481176 (Python Code)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0648. Min Range: -3.0648
Max Act: 2.6507. Min Act: -0.0001
Data Index: 1387401 (Python Code)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0648. Min Range: -3.0648
Max Act: 2.7684. Min Act: -0.0001
Data Index: 1387605 (Python Code)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19