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

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

Neuron 3361 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.3813. Min Act: -0.0000

Data Index: 193185 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.3391. Min Act: -0.0000

Data Index: 897452 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.3130. Min Act: -0.0000

Data Index: 290253 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2758. Min Act: -0.0000

Data Index: 318756 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2605. Min Act: -0.0000

Data Index: 654903 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1107591 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2729. Min Act: -0.0000

Data Index: 207530 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2575. Min Act: -0.0000

Data Index: 431075 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2448. Min Act: 0.0000

Data Index: 1271968 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2543. Min Act: -0.0000

Data Index: 1327004 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2364. Min Act: -0.0000

Data Index: 970370 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2277. Min Act: -0.0000

Data Index: 276610 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2186. Min Act: -0.0000

Data Index: 130836 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2045. Min Act: -0.0000

Data Index: 1345663 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2036. Min Act: -0.0000

Data Index: 187365 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2194. Min Act: -0.0000

Data Index: 1022474 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2295. Min Act: -0.0000

Data Index: 519721 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2126. Min Act: -0.0000

Data Index: 535066 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2218. Min Act: -0.0000

Data Index: 316536 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.3813. Min Range: -0.3813

Max Act: 0.2172. Min Act: -0.0000

Data Index: 860657 (C4 (Web Text))

Max Activating Token Index: 647