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

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

Neuron 1499 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1273923 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0608. Min Act: -0.0001

Data Index: 376563 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0494. Min Act: -0.0001

Data Index: 154401 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0498. Min Act: -0.0001

Data Index: 1086555 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0490. Min Act: -0.0001

Data Index: 896253 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0455. Min Act: -0.0001

Data Index: 496018 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0490. Min Act: -0.0001

Data Index: 46352 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0461. Min Act: -0.0001

Data Index: 831538 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0461. Min Act: -0.0001

Data Index: 713248 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0457. Min Act: -0.0001

Data Index: 1208808 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0425. Min Act: -0.0001

Data Index: 535481 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0423. Min Act: -0.0001

Data Index: 76444 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1306035 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0428. Min Act: -0.0001

Data Index: 213409 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0404. Min Act: -0.0001

Data Index: 472329 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0412. Min Act: -0.0001

Data Index: 610877 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0420. Min Act: -0.0001

Data Index: 177251 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0421. Min Act: -0.0001

Data Index: 1185826 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0386. Min Act: -0.0001

Data Index: 798473 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0420. Min Act: -0.0001

Data Index: 1205352 (C4 (Web Text))

Max Activating Token Index: 18