Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4034 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.4799. Min Range: -3.4799
Max Act: 3.4799. Min Act: -0.0001
Data Index: 378983 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4799. Min Range: -3.4799
Max Act: 3.2364. Min Act: -0.0001
Data Index: 285240 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4799. Min Range: -3.4799
Max Act: 3.3688. Min Act: -0.0001
Data Index: 183786 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4799. Min Range: -3.4799
Max Act: 3.2312. Min Act: -0.0001
Data Index: 174734 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4799. Min Range: -3.4799
Max Act: 2.7302. Min Act: -0.0001
Data Index: 41508 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4799. Min Range: -3.4799
Max Act: 2.3832. Min Act: -0.0001
Data Index: 957499 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4799. Min Range: -3.4799
Max Act: 2.8345. Min Act: -0.0001
Data Index: 1060558 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4799. Min Range: -3.4799
Max Act: 2.5721. Min Act: -0.0001
Data Index: 1288426 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4799. Min Range: -3.4799
Max Act: 2.5819. Min Act: -0.0001
Data Index: 1243201 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4799. Min Range: -3.4799
Max Act: 2.3631. Min Act: -0.0001
Data Index: 514480 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4799. Min Range: -3.4799
Max Act: 2.5099. Min Act: -0.0000
Data Index: 950209 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4799. Min Range: -3.4799
Max Act: 2.6076. Min Act: -0.0001
Data Index: 470495 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4799. Min Range: -3.4799
Max Act: 2.5922. Min Act: -0.0001
Data Index: 927380 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4799. Min Range: -3.4799
Max Act: 2.4627. Min Act: -0.0001
Data Index: 776089 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4799. Min Range: -3.4799
Max Act: 2.6929. Min Act: -0.0001
Data Index: 1074143 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4799. Min Range: -3.4799
Max Act: 2.5639. Min Act: -0.0001
Data Index: 321667 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4799. Min Range: -3.4799
Max Act: 2.4270. Min Act: -0.0001
Data Index: 912131 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4799. Min Range: -3.4799
Max Act: 2.5526. Min Act: -0.0001
Data Index: 127072 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4799. Min Range: -3.4799
Max Act: 2.5526. Min Act: -0.0001
Data Index: 496587 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4799. Min Range: -3.4799
Max Act: 2.6477. Min Act: -0.0001
Data Index: 414985 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19