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

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

Neuron 4220 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: 1.7280. Min Range: -1.7280

Max Act: 1.7280. Min Act: -0.0001

Data Index: 489950 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 1.7280. Min Range: -1.7280

Max Act: 1.6569. Min Act: -0.0001

Data Index: 899683 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 1.7280. Min Range: -1.7280

Max Act: 1.6569. Min Act: -0.0000

Data Index: 1395516 (Python Code)

Max Activating Token Index: 2

Text #3

Max Range: 1.7280. Min Range: -1.7280

Max Act: 1.6569. Min Act: -0.0001

Data Index: 158038 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 1.7280. Min Range: -1.7280

Max Act: 1.6569. Min Act: -0.0001

Data Index: 924785 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 1.7280. Min Range: -1.7280

Max Act: 1.5720. Min Act: -0.0000

Data Index: 562982 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 1.7280. Min Range: -1.7280

Max Act: 1.4438. Min Act: -0.0001

Data Index: 537121 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 1.7280. Min Range: -1.7280

Max Act: 1.3273. Min Act: -0.0001

Data Index: 839496 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 1.7280. Min Range: -1.7280

Max Act: 1.4197. Min Act: -0.0001

Data Index: 39076 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 1.7280. Min Range: -1.7280

Max Act: 1.3853. Min Act: -0.0001

Data Index: 1149664 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 1.7280. Min Range: -1.7280

Max Act: 1.2978. Min Act: -0.0001

Data Index: 341680 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 1.7280. Min Range: -1.7280

Max Act: 1.3156. Min Act: -0.0001

Data Index: 549751 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 1.7280. Min Range: -1.7280

Max Act: 1.3650. Min Act: -0.0000

Data Index: 617081 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 1.7280. Min Range: -1.7280

Max Act: 1.3613. Min Act: -0.0000

Data Index: 878235 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 1.7280. Min Range: -1.7280

Max Act: 1.3503. Min Act: -0.0001

Data Index: 1035173 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 1.7280. Min Range: -1.7280

Max Act: 1.3839. Min Act: -0.0001

Data Index: 46592 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 1.7280. Min Range: -1.7280

Max Act: 1.1385. Min Act: -0.0000

Data Index: 1247153 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 1.7280. Min Range: -1.7280

Max Act: 1.2018. Min Act: -0.0001

Data Index: 867314 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 1.7280. Min Range: -1.7280

Max Act: 1.1140. Min Act: -0.0001

Data Index: 134512 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 1.7280. Min Range: -1.7280

Max Act: 1.2261. Min Act: -0.0001

Data Index: 990441 (C4 (Web Text))

Max Activating Token Index: 1009