Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3345 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.1061. Min Range: -4.1061
Max Act: 4.1061. Min Act: -0.0001
Data Index: 222341 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1061. Min Range: -4.1061
Max Act: 3.8568. Min Act: -0.0001
Data Index: 660087 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1061. Min Range: -4.1061
Max Act: 3.6623. Min Act: -0.0001
Data Index: 592753 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1061. Min Range: -4.1061
Max Act: 3.5718. Min Act: -0.0001
Data Index: 1047120 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1061. Min Range: -4.1061
Max Act: 3.2892. Min Act: -0.0001
Data Index: 714350 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1061. Min Range: -4.1061
Max Act: 3.2538. Min Act: -0.0001
Data Index: 565307 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1061. Min Range: -4.1061
Max Act: 3.4911. Min Act: -0.0000
Data Index: 157261 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1061. Min Range: -4.1061
Max Act: 3.2717. Min Act: -0.0000
Data Index: 23104 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1061. Min Range: -4.1061
Max Act: 3.1836. Min Act: -0.0000
Data Index: 549301 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1061. Min Range: -4.1061
Max Act: 3.1647. Min Act: -0.0001
Data Index: 1046571 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1061. Min Range: -4.1061
Max Act: 2.8512. Min Act: -0.0001
Data Index: 103090 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1061. Min Range: -4.1061
Max Act: 3.1317. Min Act: -0.0001
Data Index: 1232935 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1061. Min Range: -4.1061
Max Act: 3.1842. Min Act: -0.0001
Data Index: 504828 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1061. Min Range: -4.1061
Max Act: 3.2446. Min Act: -0.0001
Data Index: 388800 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1061. Min Range: -4.1061
Max Act: 3.1160. Min Act: -0.0001
Data Index: 442725 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1061. Min Range: -4.1061
Max Act: 2.9133. Min Act: -0.0001
Data Index: 272794 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1061. Min Range: -4.1061
Max Act: 2.7020. Min Act: -0.0001
Data Index: 1186262 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1061. Min Range: -4.1061
Max Act: 2.8197. Min Act: -0.0001
Data Index: 1065996 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1061. Min Range: -4.1061
Max Act: 2.9619. Min Act: -0.0001
Data Index: 748384 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1061. Min Range: -4.1061
Max Act: 2.3591. Min Act: -0.0001
Data Index: 736596 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19