Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2871 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.2476. Min Range: -0.2476
Max Act: 0.2455. Min Act: -0.0001
Data Index: 706430 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2476. Min Range: -0.2476
Max Act: 0.2418. Min Act: -0.0001
Data Index: 1350564 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2476. Min Range: -0.2476
Max Act: 0.2214. Min Act: -0.0001
Data Index: 927377 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2476. Min Range: -0.2476
Max Act: 0.2476. Min Act: -0.0001
Data Index: 646776 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2476. Min Range: -0.2476
Max Act: 0.2188. Min Act: -0.0001
Data Index: 563348 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2476. Min Range: -0.2476
Max Act: 0.2174. Min Act: -0.0001
Data Index: 148209 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2476. Min Range: -0.2476
Max Act: 0.2220. Min Act: -0.0000
Data Index: 1237191 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2476. Min Range: -0.2476
Max Act: 0.2195. Min Act: -0.0001
Data Index: 16628 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2476. Min Range: -0.2476
Max Act: 0.2251. Min Act: -0.0001
Data Index: 1094533 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2476. Min Range: -0.2476
Max Act: 0.2266. Min Act: -0.0001
Data Index: 505915 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2476. Min Range: -0.2476
Max Act: 0.2230. Min Act: -0.0001
Data Index: 1115064 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2476. Min Range: -0.2476
Max Act: 0.2008. Min Act: -0.0001
Data Index: 933698 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2476. Min Range: -0.2476
Max Act: 0.2084. Min Act: -0.0001
Data Index: 949816 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2476. Min Range: -0.2476
Max Act: 0.2125. Min Act: -0.0001
Data Index: 146047 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2476. Min Range: -0.2476
Max Act: 0.2125. Min Act: -0.0001
Data Index: 462969 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2476. Min Range: -0.2476
Max Act: 0.2117. Min Act: -0.0001
Data Index: 524108 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2476. Min Range: -0.2476
Max Act: 0.2115. Min Act: -0.0001
Data Index: 982918 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2476. Min Range: -0.2476
Max Act: 0.2049. Min Act: -0.0001
Data Index: 357042 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2476. Min Range: -0.2476
Max Act: 0.2043. Min Act: -0.0001
Data Index: 332400 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2476. Min Range: -0.2476
Max Act: 0.2043. Min Act: -0.0001
Data Index: 1334173 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19