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

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

Neuron 2305 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1301. Min Act: -0.0000

Data Index: 460159 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1187. Min Act: -0.0000

Data Index: 258634 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1317. Min Act: -0.0000

Data Index: 467860 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1186. Min Act: -0.0000

Data Index: 401446 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1183. Min Act: -0.0000

Data Index: 955205 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1136. Min Act: -0.0000

Data Index: 1050393 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1144. Min Act: -0.0000

Data Index: 390342 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1108. Min Act: -0.0000

Data Index: 506493 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1146. Min Act: -0.0000

Data Index: 1525397 (Python Code)

Max Activating Token Index: 579

Text #9

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1052. Min Act: -0.0000

Data Index: 150495 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1088. Min Act: -0.0000

Data Index: 199074 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1055. Min Act: -0.0000

Data Index: 384774 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1023. Min Act: -0.0000

Data Index: 1276214 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1004. Min Act: -0.0000

Data Index: 1100115 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0964. Min Act: -0.0000

Data Index: 762585 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0999. Min Act: -0.0000

Data Index: 603242 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0983. Min Act: -0.0000

Data Index: 339320 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0979. Min Act: -0.0000

Data Index: 497121 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0896. Min Act: -0.0000

Data Index: 836424 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0964. Min Act: -0.0000

Data Index: 1259782 (C4 (Web Text))

Max Activating Token Index: 805