Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 442 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2569. Min Act: -0.0001

Data Index: 942716 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2480. Min Act: -0.0001

Data Index: 1143890 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1329960 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2407. Min Act: -0.0001

Data Index: 40736 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2372. Min Act: -0.0001

Data Index: 442279 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2269. Min Act: -0.0001

Data Index: 914390 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2333. Min Act: -0.0001

Data Index: 713146 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2326. Min Act: -0.0000

Data Index: 292914 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2247. Min Act: -0.0001

Data Index: 602419 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2247. Min Act: -0.0000

Data Index: 1014688 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2269. Min Act: -0.0001

Data Index: 94187 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2204. Min Act: -0.0001

Data Index: 773818 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2171. Min Act: -0.0000

Data Index: 782785 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2149. Min Act: -0.0001

Data Index: 278938 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2058. Min Act: -0.0001

Data Index: 930764 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1978. Min Act: -0.0001

Data Index: 1107716 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2051. Min Act: -0.0001

Data Index: 445398 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2037. Min Act: -0.0001

Data Index: 1202741 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2007. Min Act: -0.0000

Data Index: 534901 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.1902. Min Act: -0.0001

Data Index: 1339763 (C4 (Web Text))

Max Activating Token Index: 917