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

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

Neuron 1058 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2947. Min Range: -1.2947

Max Act: 1.2947. Min Act: -0.0000

Data Index: 1368342 (Python Code)

Max Activating Token Index: 1010

Text #1

Max Range: 1.2947. Min Range: -1.2947

Max Act: 1.1863. Min Act: -0.0000

Data Index: 120900 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 1.2947. Min Range: -1.2947

Max Act: 1.0951. Min Act: -0.0000

Data Index: 1018048 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 1.2947. Min Range: -1.2947

Max Act: 1.0650. Min Act: -0.0000

Data Index: 226702 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.9814. Min Act: -0.0000

Data Index: 1567235 (Python Code)

Max Activating Token Index: 560

Text #5

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.9885. Min Act: -0.0000

Data Index: 551444 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 1.2947. Min Range: -1.2947

Max Act: 1.0273. Min Act: -0.0000

Data Index: 108603 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.9478. Min Act: -0.0000

Data Index: 1492310 (Python Code)

Max Activating Token Index: 127

Text #8

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.9070. Min Act: -0.0000

Data Index: 1558864 (Python Code)

Max Activating Token Index: 81

Text #9

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.9282. Min Act: -0.0000

Data Index: 1638669 (Python Code)

Max Activating Token Index: 114

Text #10

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.8741. Min Act: -0.0000

Data Index: 828840 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.8885. Min Act: -0.0000

Data Index: 706443 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.9678. Min Act: -0.0000

Data Index: 1606146 (Python Code)

Max Activating Token Index: 675

Text #13

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.9262. Min Act: -0.0000

Data Index: 1491397 (Python Code)

Max Activating Token Index: 176

Text #14

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.9242. Min Act: -0.0000

Data Index: 165472 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.8373. Min Act: -0.0000

Data Index: 704272 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.8626. Min Act: -0.0000

Data Index: 1539490 (Python Code)

Max Activating Token Index: 348

Text #17

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.8931. Min Act: -0.0000

Data Index: 1531221 (Python Code)

Max Activating Token Index: 793

Text #18

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.7958. Min Act: -0.0000

Data Index: 1556255 (Python Code)

Max Activating Token Index: 464

Text #19

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.8202. Min Act: -0.0000

Data Index: 1489036 (Python Code)

Max Activating Token Index: 172