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

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

Neuron 3521 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.3692. Min Act: -0.0000

Data Index: 1654779 (Python Code)

Max Activating Token Index: 174

Text #1

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.0720. Min Act: -0.0000

Data Index: 1366739 (Python Code)

Max Activating Token Index: 929

Text #2

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.0593. Min Act: -0.0001

Data Index: 1551897 (Python Code)

Max Activating Token Index: 63

Text #3

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.0352. Min Act: -0.0000

Data Index: 1421294 (Python Code)

Max Activating Token Index: 269

Text #4

Max Range: 1.3692. Min Range: -1.3692

Max Act: 0.9926. Min Act: -0.0000

Data Index: 1608619 (Python Code)

Max Activating Token Index: 797

Text #5

Max Range: 1.3692. Min Range: -1.3692

Max Act: 0.9720. Min Act: -0.0001

Data Index: 1515258 (Python Code)

Max Activating Token Index: 884

Text #6

Max Range: 1.3692. Min Range: -1.3692

Max Act: 0.9119. Min Act: -0.0000

Data Index: 1524187 (Python Code)

Max Activating Token Index: 169

Text #7

Max Range: 1.3692. Min Range: -1.3692

Max Act: 0.9612. Min Act: -0.0001

Data Index: 1596472 (Python Code)

Max Activating Token Index: 478

Text #8

Max Range: 1.3692. Min Range: -1.3692

Max Act: 0.9569. Min Act: -0.0001

Data Index: 1573863 (Python Code)

Max Activating Token Index: 51

Text #9

Max Range: 1.3692. Min Range: -1.3692

Max Act: 0.9587. Min Act: -0.0001

Data Index: 1142582 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 1.3692. Min Range: -1.3692

Max Act: 0.8168. Min Act: -0.0001

Data Index: 1469820 (Python Code)

Max Activating Token Index: 750

Text #11

Max Range: 1.3692. Min Range: -1.3692

Max Act: 0.8931. Min Act: -0.0001

Data Index: 1450928 (Python Code)

Max Activating Token Index: 835

Text #12

Max Range: 1.3692. Min Range: -1.3692

Max Act: 0.8567. Min Act: -0.0001

Data Index: 1625457 (Python Code)

Max Activating Token Index: 52

Text #13

Max Range: 1.3692. Min Range: -1.3692

Max Act: 0.9060. Min Act: -0.0001

Data Index: 1361253 (Python Code)

Max Activating Token Index: 690

Text #14

Max Range: 1.3692. Min Range: -1.3692

Max Act: 0.9869. Min Act: -0.0001

Data Index: 1390095 (Python Code)

Max Activating Token Index: 740

Text #15

Max Range: 1.3692. Min Range: -1.3692

Max Act: 0.8579. Min Act: -0.0001

Data Index: 502379 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 1.3692. Min Range: -1.3692

Max Act: 0.9325. Min Act: -0.0000

Data Index: 1580029 (Python Code)

Max Activating Token Index: 201

Text #17

Max Range: 1.3692. Min Range: -1.3692

Max Act: 0.9018. Min Act: -0.0001

Data Index: 902830 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 1.3692. Min Range: -1.3692

Max Act: 0.9205. Min Act: -0.0001

Data Index: 1597471 (Python Code)

Max Activating Token Index: 195

Text #19

Max Range: 1.3692. Min Range: -1.3692

Max Act: 0.8362. Min Act: -0.0001

Data Index: 1641826 (Python Code)

Max Activating Token Index: 851