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

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

Neuron 1132 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: 0.4312. Min Range: -0.4312

Max Act: 0.4312. Min Act: -0.0000

Data Index: 939397 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3937. Min Act: -0.0000

Data Index: 86082 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3789. Min Act: -0.0000

Data Index: 562738 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3797. Min Act: -0.0000

Data Index: 10972 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3316. Min Act: -0.0000

Data Index: 463044 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3213. Min Act: -0.0000

Data Index: 530014 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.3066. Min Act: -0.0000

Data Index: 1038716 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.2741. Min Act: -0.0000

Data Index: 486201 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.2549. Min Act: -0.0000

Data Index: 956158 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.2615. Min Act: -0.0000

Data Index: 420255 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.2568. Min Act: -0.0000

Data Index: 1297656 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.2498. Min Act: -0.0000

Data Index: 698238 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.2144. Min Act: -0.0000

Data Index: 97305 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1448835 (Python Code)

Max Activating Token Index: 841

Text #14

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.2288. Min Act: -0.0000

Data Index: 469091 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.2248. Min Act: -0.0000

Data Index: 1089539 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.2266. Min Act: -0.0000

Data Index: 569414 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.2323. Min Act: -0.0000

Data Index: 12678 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.2171. Min Act: -0.0000

Data Index: 461043 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.4312. Min Range: -0.4312

Max Act: 0.2227. Min Act: -0.0000

Data Index: 604687 (C4 (Web Text))

Max Activating Token Index: 199