Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2292 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.6825. Min Range: -2.6825
Max Act: 2.4134. Min Act: -0.0001
Data Index: 624069 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6825. Min Range: -2.6825
Max Act: 2.6825. Min Act: -0.0001
Data Index: 43593 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6825. Min Range: -2.6825
Max Act: 2.1873. Min Act: -0.0001
Data Index: 1017209 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6825. Min Range: -2.6825
Max Act: 2.4111. Min Act: -0.0001
Data Index: 962194 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6825. Min Range: -2.6825
Max Act: 2.2570. Min Act: -0.0001
Data Index: 357284 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6825. Min Range: -2.6825
Max Act: 2.0319. Min Act: -0.0001
Data Index: 312884 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6825. Min Range: -2.6825
Max Act: 1.8998. Min Act: -0.0001
Data Index: 17696 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6825. Min Range: -2.6825
Max Act: 1.9084. Min Act: -0.0001
Data Index: 455775 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6825. Min Range: -2.6825
Max Act: 1.5349. Min Act: -0.0001
Data Index: 1340221 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6825. Min Range: -2.6825
Max Act: 1.8709. Min Act: -0.0001
Data Index: 976249 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6825. Min Range: -2.6825
Max Act: 1.9317. Min Act: -0.0001
Data Index: 1062084 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6825. Min Range: -2.6825
Max Act: 1.8712. Min Act: -0.0001
Data Index: 42221 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6825. Min Range: -2.6825
Max Act: 1.7207. Min Act: -0.0001
Data Index: 79444 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6825. Min Range: -2.6825
Max Act: 1.5475. Min Act: -0.0001
Data Index: 940072 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6825. Min Range: -2.6825
Max Act: 1.3417. Min Act: -0.0001
Data Index: 1138883 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6825. Min Range: -2.6825
Max Act: 1.3571. Min Act: -0.0001
Data Index: 101067 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6825. Min Range: -2.6825
Max Act: 1.4972. Min Act: -0.0001
Data Index: 514440 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6825. Min Range: -2.6825
Max Act: 1.3461. Min Act: -0.0001
Data Index: 237916 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6825. Min Range: -2.6825
Max Act: 1.4728. Min Act: -0.0001
Data Index: 374975 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6825. Min Range: -2.6825
Max Act: 1.5162. Min Act: -0.0001
Data Index: 417936 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #19