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

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

Neuron 2475 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2096. Min Range: -1.2096

Max Act: 1.2096. Min Act: -0.0001

Data Index: 1498523 (Python Code)

Max Activating Token Index: 982

Text #1

Max Range: 1.2096. Min Range: -1.2096

Max Act: 1.1722. Min Act: -0.0001

Data Index: 1488425 (Python Code)

Max Activating Token Index: 944

Text #2

Max Range: 1.2096. Min Range: -1.2096

Max Act: 1.1585. Min Act: -0.0001

Data Index: 1514982 (Python Code)

Max Activating Token Index: 713

Text #3

Max Range: 1.2096. Min Range: -1.2096

Max Act: 1.0883. Min Act: -0.0001

Data Index: 1629474 (Python Code)

Max Activating Token Index: 990

Text #4

Max Range: 1.2096. Min Range: -1.2096

Max Act: 1.0909. Min Act: -0.0001

Data Index: 1399597 (Python Code)

Max Activating Token Index: 917

Text #5

Max Range: 1.2096. Min Range: -1.2096

Max Act: 1.0640. Min Act: -0.0001

Data Index: 1486259 (Python Code)

Max Activating Token Index: 792

Text #6

Max Range: 1.2096. Min Range: -1.2096

Max Act: 1.0511. Min Act: -0.0001

Data Index: 1397937 (Python Code)

Max Activating Token Index: 967

Text #7

Max Range: 1.2096. Min Range: -1.2096

Max Act: 1.1443. Min Act: -0.0001

Data Index: 1635164 (Python Code)

Max Activating Token Index: 1015

Text #8

Max Range: 1.2096. Min Range: -1.2096

Max Act: 1.1105. Min Act: -0.0001

Data Index: 1403220 (Python Code)

Max Activating Token Index: 988

Text #9

Max Range: 1.2096. Min Range: -1.2096

Max Act: 1.0555. Min Act: -0.0001

Data Index: 1494901 (Python Code)

Max Activating Token Index: 899

Text #10

Max Range: 1.2096. Min Range: -1.2096

Max Act: 1.0403. Min Act: -0.0001

Data Index: 1468912 (Python Code)

Max Activating Token Index: 409

Text #11

Max Range: 1.2096. Min Range: -1.2096

Max Act: 1.1077. Min Act: -0.0001

Data Index: 1581630 (Python Code)

Max Activating Token Index: 922

Text #12

Max Range: 1.2096. Min Range: -1.2096

Max Act: 1.0372. Min Act: -0.0001

Data Index: 1456611 (Python Code)

Max Activating Token Index: 712

Text #13

Max Range: 1.2096. Min Range: -1.2096

Max Act: 1.0269. Min Act: -0.0001

Data Index: 1504053 (Python Code)

Max Activating Token Index: 990

Text #14

Max Range: 1.2096. Min Range: -1.2096

Max Act: 0.9688. Min Act: -0.0001

Data Index: 1369564 (Python Code)

Max Activating Token Index: 748

Text #15

Max Range: 1.2096. Min Range: -1.2096

Max Act: 0.9134. Min Act: -0.0001

Data Index: 1531212 (Python Code)

Max Activating Token Index: 1015

Text #16

Max Range: 1.2096. Min Range: -1.2096

Max Act: 0.9994. Min Act: -0.0001

Data Index: 1586476 (Python Code)

Max Activating Token Index: 732

Text #17

Max Range: 1.2096. Min Range: -1.2096

Max Act: 1.1162. Min Act: -0.0001

Data Index: 1605544 (Python Code)

Max Activating Token Index: 974

Text #18

Max Range: 1.2096. Min Range: -1.2096

Max Act: 1.0437. Min Act: -0.0001

Data Index: 1472058 (Python Code)

Max Activating Token Index: 955

Text #19

Max Range: 1.2096. Min Range: -1.2096

Max Act: 1.0067. Min Act: -0.0001

Data Index: 1648902 (Python Code)

Max Activating Token Index: 184