Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3375 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.2657. Min Range: -1.2657
Max Act: 1.2657. Min Act: -0.0001
Data Index: 1331128 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2657. Min Range: -1.2657
Max Act: 1.1391. Min Act: -0.0001
Data Index: 875959 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2657. Min Range: -1.2657
Max Act: 1.0563. Min Act: -0.0001
Data Index: 720591 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2657. Min Range: -1.2657
Max Act: 1.0727. Min Act: -0.0001
Data Index: 1242639 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2657. Min Range: -1.2657
Max Act: 1.0126. Min Act: -0.0001
Data Index: 600675 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2657. Min Range: -1.2657
Max Act: 1.0952. Min Act: -0.0001
Data Index: 1252206 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2657. Min Range: -1.2657
Max Act: 1.0900. Min Act: -0.0002
Data Index: 283700 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2657. Min Range: -1.2657
Max Act: 0.9754. Min Act: -0.0001
Data Index: 740374 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2657. Min Range: -1.2657
Max Act: 1.0443. Min Act: -0.0001
Data Index: 1006938 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2657. Min Range: -1.2657
Max Act: 0.9925. Min Act: -0.0001
Data Index: 458076 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2657. Min Range: -1.2657
Max Act: 0.9972. Min Act: -0.0001
Data Index: 1208930 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2657. Min Range: -1.2657
Max Act: 0.9127. Min Act: -0.0001
Data Index: 650440 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2657. Min Range: -1.2657
Max Act: 1.0164. Min Act: -0.0001
Data Index: 703444 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2657. Min Range: -1.2657
Max Act: 0.9366. Min Act: -0.0001
Data Index: 926167 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2657. Min Range: -1.2657
Max Act: 0.9907. Min Act: -0.0001
Data Index: 1268851 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2657. Min Range: -1.2657
Max Act: 1.0186. Min Act: -0.0001
Data Index: 607314 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2657. Min Range: -1.2657
Max Act: 0.9003. Min Act: -0.0001
Data Index: 353588 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2657. Min Range: -1.2657
Max Act: 0.9514. Min Act: -0.0001
Data Index: 890874 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2657. Min Range: -1.2657
Max Act: 0.8866. Min Act: -0.0001
Data Index: 581186 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2657. Min Range: -1.2657
Max Act: 0.8908. Min Act: -0.0001
Data Index: 77609 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19