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

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

Neuron 999 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.1667. Min Act: -0.0000

Data Index: 521539 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.4738. Min Act: -0.0000

Data Index: 26318 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.4094. Min Act: -0.0000

Data Index: 398181 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 3.4738. Min Range: -3.4738

Max Act: 2.6227. Min Act: -0.0000

Data Index: 737801 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.2721. Min Act: -0.0000

Data Index: 896596 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 3.4738. Min Range: -3.4738

Max Act: 2.9296. Min Act: -0.0000

Data Index: 1295737 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 3.4738. Min Range: -3.4738

Max Act: 2.8885. Min Act: -0.0000

Data Index: 1198974 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.1540. Min Act: -0.0000

Data Index: 972567 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.1131. Min Act: -0.0000

Data Index: 797171 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 3.4738. Min Range: -3.4738

Max Act: 2.9557. Min Act: -0.0000

Data Index: 362401 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 3.4738. Min Range: -3.4738

Max Act: 2.8239. Min Act: -0.0000

Data Index: 1353597 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 3.4738. Min Range: -3.4738

Max Act: 2.8086. Min Act: -0.0000

Data Index: 535579 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 3.4738. Min Range: -3.4738

Max Act: 2.6629. Min Act: -0.0000

Data Index: 652465 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 3.4738. Min Range: -3.4738

Max Act: 2.1237. Min Act: -0.0000

Data Index: 855324 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.0052. Min Act: -0.0000

Data Index: 1179390 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 3.4738. Min Range: -3.4738

Max Act: 2.7373. Min Act: -0.0000

Data Index: 1083662 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 3.4738. Min Range: -3.4738

Max Act: 2.8470. Min Act: -0.0000

Data Index: 1116002 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 3.4738. Min Range: -3.4738

Max Act: 2.6806. Min Act: -0.0000

Data Index: 600342 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 3.4738. Min Range: -3.4738

Max Act: 2.7288. Min Act: -0.0000

Data Index: 465621 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 3.4738. Min Range: -3.4738

Max Act: 2.5908. Min Act: -0.0000

Data Index: 1336367 (C4 (Web Text))

Max Activating Token Index: 564