Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2792 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8006. Min Range: -2.8006

Max Act: 2.8006. Min Act: -0.0000

Data Index: 502748 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 2.8006. Min Range: -2.8006

Max Act: 2.6512. Min Act: -0.0000

Data Index: 154088 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 2.8006. Min Range: -2.8006

Max Act: 2.4033. Min Act: -0.0000

Data Index: 876249 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 2.8006. Min Range: -2.8006

Max Act: 2.2437. Min Act: -0.0000

Data Index: 41727 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 2.8006. Min Range: -2.8006

Max Act: 2.1027. Min Act: -0.0000

Data Index: 1161567 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 2.8006. Min Range: -2.8006

Max Act: 2.2451. Min Act: -0.0000

Data Index: 352255 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 2.8006. Min Range: -2.8006

Max Act: 2.1853. Min Act: -0.0000

Data Index: 931837 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 2.8006. Min Range: -2.8006

Max Act: 2.2349. Min Act: -0.0000

Data Index: 117996 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 2.8006. Min Range: -2.8006

Max Act: 2.1278. Min Act: -0.0000

Data Index: 1145670 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 2.8006. Min Range: -2.8006

Max Act: 2.2092. Min Act: -0.0000

Data Index: 1258542 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 2.8006. Min Range: -2.8006

Max Act: 2.0985. Min Act: -0.0000

Data Index: 192149 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 2.8006. Min Range: -2.8006

Max Act: 1.9349. Min Act: -0.0000

Data Index: 302445 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 2.8006. Min Range: -2.8006

Max Act: 1.7627. Min Act: -0.0000

Data Index: 802299 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 2.8006. Min Range: -2.8006

Max Act: 2.0546. Min Act: -0.0000

Data Index: 263948 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 2.8006. Min Range: -2.8006

Max Act: 1.8202. Min Act: -0.0000

Data Index: 389607 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 2.8006. Min Range: -2.8006

Max Act: 2.1415. Min Act: -0.0000

Data Index: 593171 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 2.8006. Min Range: -2.8006

Max Act: 2.0176. Min Act: -0.0000

Data Index: 1284329 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 2.8006. Min Range: -2.8006

Max Act: 2.0300. Min Act: -0.0000

Data Index: 967382 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 2.8006. Min Range: -2.8006

Max Act: 1.9448. Min Act: -0.0000

Data Index: 209754 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 2.8006. Min Range: -2.8006

Max Act: 1.9486. Min Act: -0.0000

Data Index: 344802 (C4 (Web Text))

Max Activating Token Index: 197