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

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

Neuron 2049 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: 0.4748. Min Range: -0.4748

Max Act: 0.4548. Min Act: -0.0001

Data Index: 812613 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4748. Min Act: -0.0001

Data Index: 1032628 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4320. Min Act: -0.0001

Data Index: 844875 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4135. Min Act: -0.0001

Data Index: 1178894 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3998. Min Act: -0.0001

Data Index: 837588 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3644. Min Act: -0.0001

Data Index: 1238527 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3671. Min Act: -0.0001

Data Index: 782996 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3403. Min Act: -0.0001

Data Index: 550546 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3391. Min Act: -0.0001

Data Index: 625625 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3268. Min Act: -0.0001

Data Index: 1127748 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3526. Min Act: -0.0001

Data Index: 4550 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3408. Min Act: -0.0001

Data Index: 1113990 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.2587. Min Act: -0.0001

Data Index: 566183 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.2630. Min Act: -0.0001

Data Index: 812078 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.2500. Min Act: -0.0001

Data Index: 1320856 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.2258. Min Act: -0.0001

Data Index: 899985 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.2451. Min Act: -0.0001

Data Index: 631585 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.2497. Min Act: -0.0001

Data Index: 1014150 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.2333. Min Act: -0.0001

Data Index: 945401 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.2370. Min Act: -0.0001

Data Index: 1263522 (C4 (Web Text))

Max Activating Token Index: 517