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

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

Neuron 847 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0103. Min Range: -1.0103

Max Act: 1.0103. Min Act: -0.0000

Data Index: 550378 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8770. Min Act: -0.0000

Data Index: 1053316 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8239. Min Act: -0.0000

Data Index: 894317 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.7566. Min Act: -0.0000

Data Index: 998186 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.7748. Min Act: -0.0000

Data Index: 42111 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.7221. Min Act: -0.0001

Data Index: 9841 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.7622. Min Act: -0.0000

Data Index: 432461 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.7077. Min Act: -0.0001

Data Index: 543105 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.7129. Min Act: 0.0001

Data Index: 815038 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.6826. Min Act: -0.0001

Data Index: 967876 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1185419 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.6717. Min Act: -0.0000

Data Index: 763481 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1279014 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.6541. Min Act: -0.0000

Data Index: 21798 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.6495. Min Act: -0.0000

Data Index: 322086 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.6277. Min Act: -0.0000

Data Index: 424120 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.6345. Min Act: 0.0000

Data Index: 94068 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.6164. Min Act: -0.0001

Data Index: 222404 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.6089. Min Act: -0.0000

Data Index: 382003 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.5881. Min Act: -0.0000

Data Index: 456807 (C4 (Web Text))

Max Activating Token Index: 146