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

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

Neuron 1572 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1567. Min Range: -1.1567

Max Act: 1.1567. Min Act: -0.0001

Data Index: 1606753 (Python Code)

Max Activating Token Index: 184

Text #1

Max Range: 1.1567. Min Range: -1.1567

Max Act: 1.0164. Min Act: 0.0000

Data Index: 1508642 (Python Code)

Max Activating Token Index: 431

Text #2

Max Range: 1.1567. Min Range: -1.1567

Max Act: 0.9808. Min Act: 0.0000

Data Index: 1529289 (Python Code)

Max Activating Token Index: 137

Text #3

Max Range: 1.1567. Min Range: -1.1567

Max Act: 0.9385. Min Act: 0.0000

Data Index: 1537316 (Python Code)

Max Activating Token Index: 720

Text #4

Max Range: 1.1567. Min Range: -1.1567

Max Act: 0.9500. Min Act: 0.0000

Data Index: 1655281 (Python Code)

Max Activating Token Index: 712

Text #5

Max Range: 1.1567. Min Range: -1.1567

Max Act: 0.9271. Min Act: 0.0000

Data Index: 1380914 (Python Code)

Max Activating Token Index: 29

Text #6

Max Range: 1.1567. Min Range: -1.1567

Max Act: 0.8587. Min Act: -0.0001

Data Index: 1647393 (Python Code)

Max Activating Token Index: 866

Text #7

Max Range: 1.1567. Min Range: -1.1567

Max Act: 0.9254. Min Act: 0.0000

Data Index: 1447517 (Python Code)

Max Activating Token Index: 937

Text #8

Max Range: 1.1567. Min Range: -1.1567

Max Act: 0.8115. Min Act: -0.0000

Data Index: 1432248 (Python Code)

Max Activating Token Index: 182

Text #9

Max Range: 1.1567. Min Range: -1.1567

Max Act: 0.8578. Min Act: -0.0000

Data Index: 1574761 (Python Code)

Max Activating Token Index: 910

Text #10

Max Range: 1.1567. Min Range: -1.1567

Max Act: 0.8194. Min Act: 0.0000

Data Index: 1464988 (Python Code)

Max Activating Token Index: 886

Text #11

Max Range: 1.1567. Min Range: -1.1567

Max Act: 0.8312. Min Act: -0.0001

Data Index: 1522552 (Python Code)

Max Activating Token Index: 418

Text #12

Max Range: 1.1567. Min Range: -1.1567

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1389312 (Python Code)

Max Activating Token Index: 788

Text #13

Max Range: 1.1567. Min Range: -1.1567

Max Act: 0.7947. Min Act: -0.0001

Data Index: 1568787 (Python Code)

Max Activating Token Index: 396

Text #14

Max Range: 1.1567. Min Range: -1.1567

Max Act: 0.8008. Min Act: -0.0000

Data Index: 1508129 (Python Code)

Max Activating Token Index: 262

Text #15

Max Range: 1.1567. Min Range: -1.1567

Max Act: 0.8204. Min Act: -0.0000

Data Index: 1619297 (Python Code)

Max Activating Token Index: 578

Text #16

Max Range: 1.1567. Min Range: -1.1567

Max Act: 0.7906. Min Act: -0.0000

Data Index: 1517821 (Python Code)

Max Activating Token Index: 270

Text #17

Max Range: 1.1567. Min Range: -1.1567

Max Act: 0.7479. Min Act: -0.0001

Data Index: 1480084 (Python Code)

Max Activating Token Index: 83

Text #18

Max Range: 1.1567. Min Range: -1.1567

Max Act: 0.7555. Min Act: -0.0001

Data Index: 1601283 (Python Code)

Max Activating Token Index: 250

Text #19

Max Range: 1.1567. Min Range: -1.1567

Max Act: 0.7054. Min Act: -0.0001

Data Index: 1532844 (Python Code)

Max Activating Token Index: 325