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

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

Neuron 391 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1423. Min Act: -0.0002

Data Index: 740422 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1397. Min Act: -0.0002

Data Index: 1198460 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0711. Min Act: -0.0002

Data Index: 458548 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1141. Min Act: -0.0002

Data Index: 297487 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1115. Min Act: -0.0002

Data Index: 335785 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1207. Min Act: -0.0002

Data Index: 6191 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1386. Min Act: -0.0002

Data Index: 793802 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1319. Min Act: -0.0002

Data Index: 684694 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1212. Min Act: -0.0002

Data Index: 1284034 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1094. Min Act: -0.0002

Data Index: 1206304 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1147. Min Act: -0.0002

Data Index: 145990 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1020. Min Act: -0.0002

Data Index: 875935 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1107137 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1255. Min Act: -0.0002

Data Index: 149405 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1148. Min Act: -0.0002

Data Index: 321941 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1149. Min Act: -0.0002

Data Index: 242367 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1103. Min Act: -0.0002

Data Index: 165486 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1275. Min Act: -0.0002

Data Index: 686138 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1267. Min Act: -0.0002

Data Index: 758896 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1348. Min Act: -0.0002

Data Index: 485190 (C4 (Web Text))

Max Activating Token Index: 178