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

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

Neuron 2863 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.7651. Min Act: -0.0000

Data Index: 1107810 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.7981. Min Act: -0.0000

Data Index: 1341986 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.7320. Min Act: -0.0000

Data Index: 396552 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6616. Min Act: -0.0000

Data Index: 272675 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6802. Min Act: -0.0000

Data Index: 243119 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6320. Min Act: -0.0000

Data Index: 1066257 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6687. Min Act: -0.0000

Data Index: 562913 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6326. Min Act: -0.0000

Data Index: 549659 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6622. Min Act: -0.0000

Data Index: 494446 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1217811 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6341. Min Act: -0.0000

Data Index: 60022 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6489. Min Act: -0.0000

Data Index: 626462 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6085. Min Act: -0.0000

Data Index: 976316 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1300209 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5549. Min Act: -0.0000

Data Index: 69971 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1157570 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6733. Min Act: -0.0000

Data Index: 992214 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6254. Min Act: -0.0000

Data Index: 639627 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5779. Min Act: -0.0000

Data Index: 569536 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6464. Min Act: -0.0000

Data Index: 979224 (C4 (Web Text))

Max Activating Token Index: 991