Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2857 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.6442. Min Act: -0.0000

Data Index: 1598472 (Python Code)

Max Activating Token Index: 270

Text #1

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.4456. Min Act: -0.0000

Data Index: 1483391 (Python Code)

Max Activating Token Index: 985

Text #2

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.4136. Min Act: -0.0000

Data Index: 1615672 (Python Code)

Max Activating Token Index: 119

Text #3

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.3291. Min Act: -0.0000

Data Index: 1428413 (Python Code)

Max Activating Token Index: 113

Text #4

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.3192. Min Act: -0.0000

Data Index: 1393938 (Python Code)

Max Activating Token Index: 995

Text #5

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.3039. Min Act: -0.0000

Data Index: 1361982 (Python Code)

Max Activating Token Index: 1019

Text #6

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.3682. Min Act: -0.0000

Data Index: 1542150 (Python Code)

Max Activating Token Index: 643

Text #7

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.4154. Min Act: -0.0000

Data Index: 5820 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.3060. Min Act: -0.0000

Data Index: 1418571 (Python Code)

Max Activating Token Index: 343

Text #9

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.2521. Min Act: -0.0000

Data Index: 282482 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.2359. Min Act: -0.0000

Data Index: 1433129 (Python Code)

Max Activating Token Index: 80

Text #11

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.2325. Min Act: -0.0000

Data Index: 1372057 (Python Code)

Max Activating Token Index: 290

Text #12

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.2866. Min Act: -0.0000

Data Index: 1539209 (Python Code)

Max Activating Token Index: 853

Text #13

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.1513. Min Act: -0.0000

Data Index: 1595267 (Python Code)

Max Activating Token Index: 464

Text #14

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.1349. Min Act: -0.0000

Data Index: 766371 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.1121. Min Act: -0.0000

Data Index: 416755 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.1427. Min Act: -0.0000

Data Index: 1488719 (Python Code)

Max Activating Token Index: 963

Text #17

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.0822. Min Act: -0.0000

Data Index: 891166 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.1478. Min Act: -0.0000

Data Index: 1638403 (Python Code)

Max Activating Token Index: 886

Text #19

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.1496. Min Act: -0.0000

Data Index: 1228861 (C4 (Web Text))

Max Activating Token Index: 699