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

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

Neuron 3212 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: 0.2978. Min Range: -0.2978

Max Act: 0.2978. Min Act: -0.0001

Data Index: 499374 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2530. Min Act: -0.0001

Data Index: 1153404 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2680. Min Act: -0.0001

Data Index: 1054165 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2532. Min Act: -0.0001

Data Index: 40796 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2772. Min Act: -0.0001

Data Index: 476686 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2536. Min Act: -0.0001

Data Index: 982965 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2620. Min Act: -0.0000

Data Index: 1626359 (Python Code)

Max Activating Token Index: 327

Text #7

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2482. Min Act: -0.0000

Data Index: 1383053 (Python Code)

Max Activating Token Index: 741

Text #8

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2466. Min Act: -0.0001

Data Index: 1300293 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2388. Min Act: -0.0001

Data Index: 1158241 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1530254 (Python Code)

Max Activating Token Index: 784

Text #11

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1603693 (Python Code)

Max Activating Token Index: 799

Text #12

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2599. Min Act: -0.0001

Data Index: 300261 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2378. Min Act: -0.0000

Data Index: 1519293 (Python Code)

Max Activating Token Index: 567

Text #14

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2177. Min Act: -0.0000

Data Index: 935132 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2347. Min Act: -0.0001

Data Index: 402145 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2412. Min Act: -0.0000

Data Index: 1635092 (Python Code)

Max Activating Token Index: 796

Text #17

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2371. Min Act: -0.0001

Data Index: 357798 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2373. Min Act: -0.0001

Data Index: 505720 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2258. Min Act: -0.0001

Data Index: 270096 (C4 (Web Text))

Max Activating Token Index: 555