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

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

Neuron 6105 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8059. Min Range: -1.8059

Max Act: 1.8059. Min Act: -0.0000

Data Index: 714083 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 1.8059. Min Range: -1.8059

Max Act: 1.7020. Min Act: -0.0000

Data Index: 716513 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 1.8059. Min Range: -1.8059

Max Act: 1.7462. Min Act: -0.0000

Data Index: 76039 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 1.8059. Min Range: -1.8059

Max Act: 1.7166. Min Act: -0.0000

Data Index: 520357 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 1.8059. Min Range: -1.8059

Max Act: 1.7180. Min Act: -0.0000

Data Index: 240047 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 1.8059. Min Range: -1.8059

Max Act: 1.6965. Min Act: -0.0000

Data Index: 1261220 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 1.8059. Min Range: -1.8059

Max Act: 1.5332. Min Act: -0.0000

Data Index: 256719 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 1.8059. Min Range: -1.8059

Max Act: 1.5165. Min Act: -0.0000

Data Index: 685074 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 1.8059. Min Range: -1.8059

Max Act: 1.5828. Min Act: -0.0000

Data Index: 272535 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 1.8059. Min Range: -1.8059

Max Act: 1.4607. Min Act: -0.0000

Data Index: 1021931 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 1.8059. Min Range: -1.8059

Max Act: 1.4641. Min Act: -0.0000

Data Index: 140366 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 1.8059. Min Range: -1.8059

Max Act: 1.4525. Min Act: -0.0000

Data Index: 62093 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 1.8059. Min Range: -1.8059

Max Act: 1.3489. Min Act: -0.0000

Data Index: 1116592 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 1.8059. Min Range: -1.8059

Max Act: 1.4231. Min Act: -0.0000

Data Index: 511070 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 1.8059. Min Range: -1.8059

Max Act: 1.4144. Min Act: -0.0000

Data Index: 473825 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 1.8059. Min Range: -1.8059

Max Act: 1.3022. Min Act: -0.0000

Data Index: 1012364 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 1.8059. Min Range: -1.8059

Max Act: 1.4681. Min Act: -0.0000

Data Index: 1127287 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 1.8059. Min Range: -1.8059

Max Act: 1.4555. Min Act: -0.0000

Data Index: 1251952 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 1.8059. Min Range: -1.8059

Max Act: 1.6290. Min Act: -0.0000

Data Index: 757153 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 1.8059. Min Range: -1.8059

Max Act: 1.4425. Min Act: -0.0000

Data Index: 1292705 (C4 (Web Text))

Max Activating Token Index: 450