Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2969 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.8532. Min Range: -2.8532
Max Act: 2.8532. Min Act: -0.0001
Data Index: 74042 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8532. Min Range: -2.8532
Max Act: 2.5244. Min Act: -0.0001
Data Index: 836857 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8532. Min Range: -2.8532
Max Act: 2.6310. Min Act: -0.0001
Data Index: 258412 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8532. Min Range: -2.8532
Max Act: 2.5701. Min Act: -0.0001
Data Index: 1040950 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8532. Min Range: -2.8532
Max Act: 2.3603. Min Act: -0.0001
Data Index: 795020 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8532. Min Range: -2.8532
Max Act: 2.4443. Min Act: -0.0001
Data Index: 176922 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8532. Min Range: -2.8532
Max Act: 2.4166. Min Act: -0.0001
Data Index: 404111 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8532. Min Range: -2.8532
Max Act: 2.4129. Min Act: -0.0001
Data Index: 981650 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8532. Min Range: -2.8532
Max Act: 2.3885. Min Act: -0.0001
Data Index: 34359 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8532. Min Range: -2.8532
Max Act: 2.3557. Min Act: -0.0001
Data Index: 668683 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8532. Min Range: -2.8532
Max Act: 2.3693. Min Act: -0.0001
Data Index: 815971 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8532. Min Range: -2.8532
Max Act: 2.2125. Min Act: -0.0001
Data Index: 766596 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8532. Min Range: -2.8532
Max Act: 2.3029. Min Act: -0.0001
Data Index: 212510 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8532. Min Range: -2.8532
Max Act: 2.4193. Min Act: -0.0001
Data Index: 1286490 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8532. Min Range: -2.8532
Max Act: 2.1686. Min Act: -0.0001
Data Index: 1183878 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8532. Min Range: -2.8532
Max Act: 2.2850. Min Act: -0.0001
Data Index: 5512 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8532. Min Range: -2.8532
Max Act: 2.2581. Min Act: -0.0001
Data Index: 1251505 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8532. Min Range: -2.8532
Max Act: 2.2439. Min Act: -0.0001
Data Index: 510645 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8532. Min Range: -2.8532
Max Act: 2.3556. Min Act: -0.0001
Data Index: 978154 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8532. Min Range: -2.8532
Max Act: 2.1720. Min Act: -0.0001
Data Index: 733973 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19