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

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

Neuron 3906 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: 0.3367. Min Range: -0.3367

Max Act: 0.3367. Min Act: -0.0000

Data Index: 323815 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2605. Min Act: -0.0000

Data Index: 132412 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2566. Min Act: -0.0000

Data Index: 966476 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2578. Min Act: -0.0000

Data Index: 862009 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2459. Min Act: -0.0000

Data Index: 59119 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2424. Min Act: 0.0000

Data Index: 919246 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2388. Min Act: -0.0000

Data Index: 659446 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2273. Min Act: -0.0000

Data Index: 265749 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2510. Min Act: -0.0000

Data Index: 372805 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2157. Min Act: -0.0000

Data Index: 269282 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1167720 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2176. Min Act: -0.0000

Data Index: 110727 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2067. Min Act: -0.0000

Data Index: 1072554 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2122. Min Act: -0.0000

Data Index: 706881 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2119. Min Act: -0.0000

Data Index: 1226536 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2108. Min Act: -0.0000

Data Index: 1365034 (Python Code)

Max Activating Token Index: 701

Text #16

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2107. Min Act: -0.0000

Data Index: 436720 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2138. Min Act: -0.0000

Data Index: 967348 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1258410 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.3367. Min Range: -0.3367

Max Act: 0.2067. Min Act: -0.0000

Data Index: 740312 (C4 (Web Text))

Max Activating Token Index: 92