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

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

Neuron 5107 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.7711. Min Act: -0.0000

Data Index: 352440 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.6302. Min Act: -0.0000

Data Index: 747529 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.4973. Min Act: -0.0000

Data Index: 233450 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.4116. Min Act: -0.0000

Data Index: 883155 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.3226. Min Act: -0.0000

Data Index: 716796 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.3869. Min Act: -0.0000

Data Index: 798177 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.3120. Min Act: -0.0000

Data Index: 1343671 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.2377. Min Act: -0.0000

Data Index: 1226656 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.2067. Min Act: -0.0000

Data Index: 661391 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.1836. Min Act: -0.0000

Data Index: 1289804 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.1294. Min Act: -0.0000

Data Index: 1271709 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.1244. Min Act: -0.0000

Data Index: 640031 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.0506. Min Act: -0.0000

Data Index: 586916 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.0405. Min Act: -0.0000

Data Index: 1282183 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.0776. Min Act: -0.0000

Data Index: 345488 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.0719. Min Act: -0.0000

Data Index: 316198 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.0724. Min Act: -0.0000

Data Index: 779157 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.0542. Min Act: -0.0000

Data Index: 16704 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.0543. Min Act: -0.0000

Data Index: 1189889 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.0337. Min Act: -0.0000

Data Index: 1100660 (C4 (Web Text))

Max Activating Token Index: 589