Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 71 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 6.5859. Min Range: -6.5859
Max Act: 6.5859. Min Act: -0.0001
Data Index: 946918 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5859. Min Range: -6.5859
Max Act: 5.3692. Min Act: -0.0001
Data Index: 734565 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5859. Min Range: -6.5859
Max Act: 4.4031. Min Act: -0.0001
Data Index: 772339 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5859. Min Range: -6.5859
Max Act: 4.3201. Min Act: -0.0001
Data Index: 529609 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5859. Min Range: -6.5859
Max Act: 4.2307. Min Act: -0.0001
Data Index: 1008472 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5859. Min Range: -6.5859
Max Act: 4.1836. Min Act: -0.0001
Data Index: 189814 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5859. Min Range: -6.5859
Max Act: 3.9764. Min Act: -0.0001
Data Index: 373735 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5859. Min Range: -6.5859
Max Act: 4.4433. Min Act: -0.0001
Data Index: 1278839 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5859. Min Range: -6.5859
Max Act: 4.1176. Min Act: -0.0001
Data Index: 789534 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5859. Min Range: -6.5859
Max Act: 3.9490. Min Act: -0.0001
Data Index: 240124 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5859. Min Range: -6.5859
Max Act: 4.0795. Min Act: -0.0001
Data Index: 1357614 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5859. Min Range: -6.5859
Max Act: 4.0781. Min Act: -0.0001
Data Index: 483950 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5859. Min Range: -6.5859
Max Act: 4.1684. Min Act: -0.0001
Data Index: 892673 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5859. Min Range: -6.5859
Max Act: 4.0127. Min Act: -0.0001
Data Index: 682639 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5859. Min Range: -6.5859
Max Act: 4.1982. Min Act: -0.0001
Data Index: 198525 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5859. Min Range: -6.5859
Max Act: 4.0257. Min Act: -0.0001
Data Index: 1343495 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5859. Min Range: -6.5859
Max Act: 3.8129. Min Act: -0.0001
Data Index: 1073953 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5859. Min Range: -6.5859
Max Act: 3.9728. Min Act: -0.0001
Data Index: 370609 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5859. Min Range: -6.5859
Max Act: 3.7908. Min Act: -0.0001
Data Index: 870360 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5859. Min Range: -6.5859
Max Act: 3.9197. Min Act: -0.0001
Data Index: 719836 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19