Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4030 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.0501. Min Range: -2.0501
Max Act: 2.0501. Min Act: -0.0001
Data Index: 740192 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0501. Min Range: -2.0501
Max Act: 1.9956. Min Act: -0.0001
Data Index: 34168 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0501. Min Range: -2.0501
Max Act: 1.9686. Min Act: -0.0001
Data Index: 78266 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0501. Min Range: -2.0501
Max Act: 1.9637. Min Act: -0.0001
Data Index: 843012 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0501. Min Range: -2.0501
Max Act: 1.9678. Min Act: -0.0001
Data Index: 461731 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0501. Min Range: -2.0501
Max Act: 1.8688. Min Act: -0.0001
Data Index: 729085 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0501. Min Range: -2.0501
Max Act: 1.7533. Min Act: -0.0001
Data Index: 280917 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0501. Min Range: -2.0501
Max Act: 1.6621. Min Act: -0.0001
Data Index: 478885 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0501. Min Range: -2.0501
Max Act: 1.6146. Min Act: -0.0001
Data Index: 391493 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0501. Min Range: -2.0501
Max Act: 1.7507. Min Act: -0.0001
Data Index: 115219 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0501. Min Range: -2.0501
Max Act: 1.6221. Min Act: -0.0001
Data Index: 27748 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0501. Min Range: -2.0501
Max Act: 1.5975. Min Act: -0.0001
Data Index: 167034 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0501. Min Range: -2.0501
Max Act: 1.4835. Min Act: -0.0001
Data Index: 1012217 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0501. Min Range: -2.0501
Max Act: 1.5193. Min Act: -0.0001
Data Index: 201636 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0501. Min Range: -2.0501
Max Act: 1.5537. Min Act: -0.0001
Data Index: 710187 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0501. Min Range: -2.0501
Max Act: 1.6366. Min Act: -0.0001
Data Index: 115948 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0501. Min Range: -2.0501
Max Act: 1.5670. Min Act: -0.0001
Data Index: 520280 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0501. Min Range: -2.0501
Max Act: 1.5485. Min Act: -0.0001
Data Index: 373214 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0501. Min Range: -2.0501
Max Act: 1.4789. Min Act: -0.0001
Data Index: 1301788 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0501. Min Range: -2.0501
Max Act: 1.5685. Min Act: -0.0001
Data Index: 971858 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19