Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3045 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1172542 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0418. Min Act: -0.0003

Data Index: 176384 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0384. Min Act: -0.0003

Data Index: 765153 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0399. Min Act: -0.0003

Data Index: 1232858 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0343. Min Act: -0.0003

Data Index: 455719 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1344787 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0359. Min Act: -0.0003

Data Index: 1322952 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0341. Min Act: -0.0003

Data Index: 1461599 (Python Code)

Max Activating Token Index: 88

Text #8

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0311. Min Act: -0.0003

Data Index: 847346 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0334. Min Act: -0.0003

Data Index: 750257 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0394. Min Act: -0.0003

Data Index: 981995 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0332. Min Act: -0.0003

Data Index: 503057 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0336. Min Act: -0.0003

Data Index: 623998 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0330. Min Act: -0.0003

Data Index: 803736 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0326. Min Act: -0.0003

Data Index: 506632 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0322. Min Act: -0.0003

Data Index: 917766 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0322. Min Act: -0.0003

Data Index: 368285 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1205061 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0320. Min Act: -0.0003

Data Index: 972256 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0306. Min Act: -0.0003

Data Index: 362599 (C4 (Web Text))

Max Activating Token Index: 156