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

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

Neuron 3739 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: 0.2064. Min Range: -0.2064

Max Act: 0.2064. Min Act: -0.0000

Data Index: 526238 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.1036. Min Act: -0.0000

Data Index: 71501 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.0495. Min Act: -0.0000

Data Index: 516304 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.0509. Min Act: -0.0000

Data Index: 859385 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.0356. Min Act: -0.0000

Data Index: 1235501 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.0468. Min Act: -0.0000

Data Index: 618454 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.0415. Min Act: -0.0000

Data Index: 515838 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.0461. Min Act: -0.0000

Data Index: 860245 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.0340. Min Act: -0.0000

Data Index: 929 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.0408. Min Act: -0.0000

Data Index: 640768 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.0369. Min Act: -0.0000

Data Index: 673425 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.0358. Min Act: -0.0000

Data Index: 852999 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.0335. Min Act: -0.0000

Data Index: 267869 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.0324. Min Act: -0.0000

Data Index: 988357 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.0285. Min Act: -0.0000

Data Index: 1431328 (Python Code)

Max Activating Token Index: 749

Text #15

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.0346. Min Act: -0.0000

Data Index: 852440 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.0318. Min Act: -0.0000

Data Index: 298650 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.0318. Min Act: -0.0000

Data Index: 69940 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.0340. Min Act: -0.0000

Data Index: 1445748 (Python Code)

Max Activating Token Index: 309

Text #19

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.0316. Min Act: -0.0000

Data Index: 1239586 (C4 (Web Text))

Max Activating Token Index: 4