Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1861 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0353. Min Act: -0.0006

Data Index: 882098 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0339. Min Act: -0.0006

Data Index: 773770 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0336. Min Act: -0.0006

Data Index: 926442 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0320. Min Act: -0.0006

Data Index: 643977 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0313. Min Act: -0.0006

Data Index: 771315 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0316. Min Act: -0.0006

Data Index: 403026 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0331. Min Act: -0.0006

Data Index: 49576 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0314. Min Act: -0.0006

Data Index: 595242 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0316. Min Act: -0.0006

Data Index: 1235604 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0323. Min Act: -0.0006

Data Index: 1023745 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0318. Min Act: -0.0006

Data Index: 418746 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0319. Min Act: -0.0006

Data Index: 1024910 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0326. Min Act: -0.0006

Data Index: 490164 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0310. Min Act: -0.0006

Data Index: 1024005 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0291. Min Act: -0.0006

Data Index: 648066 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0314. Min Act: -0.0006

Data Index: 1191778 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0314. Min Act: -0.0006

Data Index: 409073 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0305. Min Act: -0.0006

Data Index: 1317153 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0313. Min Act: -0.0006

Data Index: 654377 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0320. Min Act: -0.0006

Data Index: 134996 (C4 (Web Text))

Max Activating Token Index: 743