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

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

Neuron 5407 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1864. Min Act: -0.0001

Data Index: 1196527 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1712. Min Act: -0.0001

Data Index: 839099 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1524. Min Act: -0.0001

Data Index: 556502 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1733. Min Act: -0.0001

Data Index: 1083349 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1667. Min Act: -0.0001

Data Index: 273016 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1558. Min Act: -0.0001

Data Index: 1145665 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1400. Min Act: -0.0001

Data Index: 217975 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1268. Min Act: -0.0001

Data Index: 416554 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1489. Min Act: -0.0001

Data Index: 1019048 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1293. Min Act: -0.0001

Data Index: 1026328 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1366. Min Act: -0.0001

Data Index: 988969 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1348. Min Act: -0.0001

Data Index: 1228217 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1212. Min Act: -0.0001

Data Index: 1239175 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1334. Min Act: -0.0001

Data Index: 426486 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1332. Min Act: -0.0001

Data Index: 1041799 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1388. Min Act: -0.0001

Data Index: 998080 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1286. Min Act: -0.0001

Data Index: 1128530 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1322. Min Act: -0.0001

Data Index: 486856 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1328. Min Act: -0.0001

Data Index: 946819 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1280. Min Act: -0.0001

Data Index: 1285417 (C4 (Web Text))

Max Activating Token Index: 406