Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3402 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.4472. Min Act: -0.0001

Data Index: 436049 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3765. Min Act: -0.0001

Data Index: 1159299 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.2860. Min Act: -0.0001

Data Index: 417170 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3516. Min Act: -0.0001

Data Index: 254993 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3384. Min Act: -0.0001

Data Index: 984443 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.2767. Min Act: -0.0001

Data Index: 747618 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3554. Min Act: -0.0001

Data Index: 893929 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.2339. Min Act: -0.0001

Data Index: 826436 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.2281. Min Act: -0.0001

Data Index: 427040 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3009. Min Act: -0.0001

Data Index: 1145324 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.2296. Min Act: -0.0000

Data Index: 636637 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.2825. Min Act: -0.0001

Data Index: 1302631 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.2520. Min Act: -0.0001

Data Index: 927080 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.2835. Min Act: -0.0000

Data Index: 407233 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3152. Min Act: -0.0001

Data Index: 337442 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.1527. Min Act: -0.0001

Data Index: 1024116 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.1398. Min Act: -0.0001

Data Index: 601395 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3285. Min Act: -0.0001

Data Index: 1356218 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.2005. Min Act: -0.0001

Data Index: 4476 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.2660. Min Act: -0.0001

Data Index: 97498 (C4 (Web Text))

Max Activating Token Index: 984