Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 591 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7332. Min Range: -2.7332

Max Act: 2.7332. Min Act: -0.0000

Data Index: 95293 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 2.7332. Min Range: -2.7332

Max Act: 2.4815. Min Act: -0.0000

Data Index: 117737 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 2.7332. Min Range: -2.7332

Max Act: 2.3772. Min Act: -0.0000

Data Index: 354454 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 2.7332. Min Range: -2.7332

Max Act: 2.5353. Min Act: -0.0000

Data Index: 597988 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 2.7332. Min Range: -2.7332

Max Act: 2.1219. Min Act: -0.0000

Data Index: 1282111 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 2.7332. Min Range: -2.7332

Max Act: 2.2287. Min Act: -0.0000

Data Index: 632103 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 2.7332. Min Range: -2.7332

Max Act: 2.3211. Min Act: -0.0000

Data Index: 1055455 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 2.7332. Min Range: -2.7332

Max Act: 2.2950. Min Act: -0.0000

Data Index: 258167 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 2.7332. Min Range: -2.7332

Max Act: 2.3520. Min Act: -0.0000

Data Index: 545473 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 2.7332. Min Range: -2.7332

Max Act: 2.2482. Min Act: -0.0000

Data Index: 627267 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 2.7332. Min Range: -2.7332

Max Act: 2.2218. Min Act: -0.0000

Data Index: 422173 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 2.7332. Min Range: -2.7332

Max Act: 2.1947. Min Act: -0.0000

Data Index: 105785 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 2.7332. Min Range: -2.7332

Max Act: 2.1777. Min Act: -0.0000

Data Index: 26724 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 2.7332. Min Range: -2.7332

Max Act: 2.1339. Min Act: -0.0000

Data Index: 232889 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 2.7332. Min Range: -2.7332

Max Act: 2.1309. Min Act: -0.0000

Data Index: 625776 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 2.7332. Min Range: -2.7332

Max Act: 2.2596. Min Act: -0.0000

Data Index: 754454 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 2.7332. Min Range: -2.7332

Max Act: 2.1172. Min Act: -0.0000

Data Index: 723214 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 2.7332. Min Range: -2.7332

Max Act: 2.2277. Min Act: -0.0000

Data Index: 1349731 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 2.7332. Min Range: -2.7332

Max Act: 2.2143. Min Act: -0.0000

Data Index: 1300664 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 2.7332. Min Range: -2.7332

Max Act: 2.0876. Min Act: -0.0000

Data Index: 1127700 (C4 (Web Text))

Max Activating Token Index: 80