Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1575 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2235. Min Range: -1.2235

Max Act: 1.2235. Min Act: -0.0001

Data Index: 1263089 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 1.2235. Min Range: -1.2235

Max Act: 1.1711. Min Act: -0.0001

Data Index: 1043682 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 1.2235. Min Range: -1.2235

Max Act: 1.0101. Min Act: -0.0000

Data Index: 1020983 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.9872. Min Act: -0.0001

Data Index: 182754 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.9053. Min Act: -0.0001

Data Index: 481929 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.8869. Min Act: -0.0000

Data Index: 1003840 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.8830. Min Act: -0.0001

Data Index: 1129083 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.8916. Min Act: -0.0000

Data Index: 1059064 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.7805. Min Act: -0.0000

Data Index: 831976 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1340195 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.7370. Min Act: -0.0001

Data Index: 344267 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.8380. Min Act: -0.0001

Data Index: 477509 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.7843. Min Act: -0.0000

Data Index: 377913 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.7952. Min Act: -0.0001

Data Index: 728867 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.7929. Min Act: -0.0001

Data Index: 804150 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.7437. Min Act: -0.0001

Data Index: 697443 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.7858. Min Act: -0.0000

Data Index: 24668 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.7270. Min Act: -0.0001

Data Index: 582101 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.7532. Min Act: -0.0000

Data Index: 677602 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 1.2235. Min Range: -1.2235

Max Act: 0.7452. Min Act: -0.0000

Data Index: 380927 (C4 (Web Text))

Max Activating Token Index: 299