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

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

Neuron 2081 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4437. Min Act: -0.0001

Data Index: 892550 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4284. Min Act: -0.0001

Data Index: 923602 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4199. Min Act: -0.0001

Data Index: 136414 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4204. Min Act: -0.0001

Data Index: 438042 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4042. Min Act: -0.0001

Data Index: 249248 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4039. Min Act: -0.0000

Data Index: 1203171 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4233. Min Act: -0.0001

Data Index: 932605 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1323676 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3671. Min Act: -0.0001

Data Index: 373522 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3661. Min Act: -0.0001

Data Index: 477805 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3118. Min Act: -0.0001

Data Index: 870954 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3718. Min Act: -0.0001

Data Index: 1245975 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3222. Min Act: -0.0001

Data Index: 1052146 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4169. Min Act: -0.0000

Data Index: 653205 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3771. Min Act: -0.0000

Data Index: 90888 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3523. Min Act: -0.0000

Data Index: 1447533 (Python Code)

Max Activating Token Index: 608

Text #16

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3564. Min Act: -0.0001

Data Index: 154847 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3617. Min Act: -0.0001

Data Index: 751402 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3407. Min Act: -0.0000

Data Index: 1479766 (Python Code)

Max Activating Token Index: 192

Text #19

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1499664 (Python Code)

Max Activating Token Index: 180