Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2578 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.6864. Min Range: -2.6864
Max Act: 2.6864. Min Act: -0.0001
Data Index: 913436 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6864. Min Range: -2.6864
Max Act: 2.4615. Min Act: -0.0001
Data Index: 721474 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6864. Min Range: -2.6864
Max Act: 2.4577. Min Act: -0.0001
Data Index: 124171 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6864. Min Range: -2.6864
Max Act: 2.3477. Min Act: -0.0001
Data Index: 795217 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6864. Min Range: -2.6864
Max Act: 2.2552. Min Act: -0.0001
Data Index: 1298232 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6864. Min Range: -2.6864
Max Act: 1.9819. Min Act: -0.0001
Data Index: 160295 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6864. Min Range: -2.6864
Max Act: 1.9691. Min Act: -0.0001
Data Index: 671975 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6864. Min Range: -2.6864
Max Act: 1.9881. Min Act: -0.0001
Data Index: 955005 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6864. Min Range: -2.6864
Max Act: 2.0319. Min Act: -0.0001
Data Index: 152934 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6864. Min Range: -2.6864
Max Act: 1.9475. Min Act: -0.0001
Data Index: 256542 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6864. Min Range: -2.6864
Max Act: 2.0314. Min Act: -0.0001
Data Index: 968138 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6864. Min Range: -2.6864
Max Act: 2.0373. Min Act: -0.0001
Data Index: 585350 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6864. Min Range: -2.6864
Max Act: 2.0378. Min Act: -0.0001
Data Index: 668060 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6864. Min Range: -2.6864
Max Act: 1.9663. Min Act: -0.0001
Data Index: 172741 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6864. Min Range: -2.6864
Max Act: 2.0666. Min Act: -0.0001
Data Index: 561558 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6864. Min Range: -2.6864
Max Act: 2.2246. Min Act: -0.0001
Data Index: 779866 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6864. Min Range: -2.6864
Max Act: 1.9966. Min Act: -0.0001
Data Index: 1181549 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6864. Min Range: -2.6864
Max Act: 1.9307. Min Act: -0.0001
Data Index: 648501 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6864. Min Range: -2.6864
Max Act: 1.7432. Min Act: -0.0001
Data Index: 700329 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6864. Min Range: -2.6864
Max Act: 2.0865. Min Act: -0.0001
Data Index: 78578 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19