Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4986 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4946. Min Range: -1.4946

Max Act: 1.4946. Min Act: -0.0000

Data Index: 612206 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 1.4946. Min Range: -1.4946

Max Act: 1.0814. Min Act: -0.0000

Data Index: 268068 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 1.4946. Min Range: -1.4946

Max Act: 1.1274. Min Act: -0.0000

Data Index: 663720 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 1.4946. Min Range: -1.4946

Max Act: 1.1213. Min Act: -0.0000

Data Index: 18840 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 1.4946. Min Range: -1.4946

Max Act: 1.0872. Min Act: -0.0000

Data Index: 717943 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.8973. Min Act: -0.0000

Data Index: 369174 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.7852. Min Act: -0.0000

Data Index: 426046 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.7494. Min Act: -0.0000

Data Index: 1086995 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.7154. Min Act: -0.0000

Data Index: 1633348 (Python Code)

Max Activating Token Index: 236

Text #9

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.7629. Min Act: -0.0000

Data Index: 256844 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.7268. Min Act: -0.0000

Data Index: 269159 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.7025. Min Act: -0.0000

Data Index: 1333015 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1134123 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.6055. Min Act: -0.0000

Data Index: 1446752 (Python Code)

Max Activating Token Index: 966

Text #14

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.5767. Min Act: -0.0000

Data Index: 1175735 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.5550. Min Act: -0.0000

Data Index: 547813 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.5801. Min Act: -0.0000

Data Index: 322011 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.5623. Min Act: -0.0000

Data Index: 1061256 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.5614. Min Act: -0.0000

Data Index: 391714 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 1.4946. Min Range: -1.4946

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1549645 (Python Code)

Max Activating Token Index: 547