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

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

Neuron 4024 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2728. Min Act: -0.0000

Data Index: 465956 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2619. Min Act: -0.0000

Data Index: 1335757 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2433. Min Act: -0.0000

Data Index: 210461 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2414. Min Act: -0.0000

Data Index: 746601 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2469. Min Act: -0.0000

Data Index: 1652960 (Python Code)

Max Activating Token Index: 837

Text #5

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2433. Min Act: -0.0000

Data Index: 227670 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2351. Min Act: -0.0000

Data Index: 121514 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1457753 (Python Code)

Max Activating Token Index: 344

Text #8

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2084. Min Act: -0.0000

Data Index: 562434 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2280. Min Act: -0.0000

Data Index: 1611263 (Python Code)

Max Activating Token Index: 773

Text #10

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2117. Min Act: -0.0000

Data Index: 590553 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2089. Min Act: -0.0000

Data Index: 801127 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2246. Min Act: -0.0000

Data Index: 612540 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2066. Min Act: -0.0000

Data Index: 518860 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1386217 (Python Code)

Max Activating Token Index: 763

Text #15

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1939. Min Act: -0.0000

Data Index: 609779 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2088. Min Act: -0.0000

Data Index: 715983 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1458715 (Python Code)

Max Activating Token Index: 473

Text #18

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1861. Min Act: -0.0000

Data Index: 574813 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1176242 (C4 (Web Text))

Max Activating Token Index: 680