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

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

Neuron 641 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.3223. Min Act: -0.0000

Data Index: 510411 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.3729. Min Act: -0.0001

Data Index: 138772 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1242417 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.3176. Min Act: -0.0000

Data Index: 96340 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2942. Min Act: -0.0000

Data Index: 325107 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2733. Min Act: -0.0000

Data Index: 294170 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2480. Min Act: -0.0001

Data Index: 859823 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2575. Min Act: -0.0001

Data Index: 1163091 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2241. Min Act: -0.0001

Data Index: 1080118 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2399. Min Act: -0.0001

Data Index: 973241 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2259. Min Act: -0.0000

Data Index: 634434 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2393. Min Act: -0.0001

Data Index: 1220039 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2278. Min Act: -0.0001

Data Index: 61560 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2058. Min Act: -0.0001

Data Index: 178605 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2076. Min Act: -0.0001

Data Index: 758887 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2160. Min Act: -0.0001

Data Index: 986127 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2055. Min Act: -0.0000

Data Index: 517363 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.1943. Min Act: -0.0001

Data Index: 723159 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1410507 (Python Code)

Max Activating Token Index: 108

Text #19

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.1865. Min Act: -0.0000

Data Index: 613123 (C4 (Web Text))

Max Activating Token Index: 813