Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2352 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3032. Min Range: -1.3032

Max Act: 1.3032. Min Act: -0.0001

Data Index: 1445830 (Python Code)

Max Activating Token Index: 892

Text #1

Max Range: 1.3032. Min Range: -1.3032

Max Act: 1.2937. Min Act: -0.0000

Data Index: 534603 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 1.3032. Min Range: -1.3032

Max Act: 1.2831. Min Act: -0.0000

Data Index: 1055398 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 1.3032. Min Range: -1.3032

Max Act: 1.2658. Min Act: 0.0000

Data Index: 1030523 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 1.3032. Min Range: -1.3032

Max Act: 1.2083. Min Act: -0.0000

Data Index: 288252 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 1.3032. Min Range: -1.3032

Max Act: 1.1609. Min Act: -0.0001

Data Index: 1558126 (Python Code)

Max Activating Token Index: 762

Text #6

Max Range: 1.3032. Min Range: -1.3032

Max Act: 1.1561. Min Act: -0.0000

Data Index: 157132 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 1.3032. Min Range: -1.3032

Max Act: 1.1431. Min Act: -0.0001

Data Index: 939564 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 1.3032. Min Range: -1.3032

Max Act: 1.0741. Min Act: 0.0000

Data Index: 8841 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 1.3032. Min Range: -1.3032

Max Act: 1.0881. Min Act: -0.0001

Data Index: 49587 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 1.3032. Min Range: -1.3032

Max Act: 1.1170. Min Act: -0.0001

Data Index: 88089 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 1.3032. Min Range: -1.3032

Max Act: 1.0241. Min Act: 0.0000

Data Index: 721101 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 1.3032. Min Range: -1.3032

Max Act: 1.1228. Min Act: 0.0000

Data Index: 760500 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 1.3032. Min Range: -1.3032

Max Act: 1.0825. Min Act: -0.0000

Data Index: 888083 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 1.3032. Min Range: -1.3032

Max Act: 1.0043. Min Act: -0.0000

Data Index: 654 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 1.3032. Min Range: -1.3032

Max Act: 1.1357. Min Act: -0.0000

Data Index: 264586 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 1.3032. Min Range: -1.3032

Max Act: 1.0334. Min Act: -0.0000

Data Index: 457514 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 1.3032. Min Range: -1.3032

Max Act: 1.0636. Min Act: -0.0000

Data Index: 360549 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 1.3032. Min Range: -1.3032

Max Act: 1.0319. Min Act: 0.0001

Data Index: 1105919 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 1.3032. Min Range: -1.3032

Max Act: 0.9957. Min Act: -0.0001

Data Index: 199652 (C4 (Web Text))

Max Activating Token Index: 432