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

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

Neuron 2877 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4788. Min Range: -1.4788

Max Act: 1.4788. Min Act: -0.0001

Data Index: 577996 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 1.4788. Min Range: -1.4788

Max Act: 1.3472. Min Act: -0.0001

Data Index: 1277915 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 1.4788. Min Range: -1.4788

Max Act: 1.3545. Min Act: -0.0001

Data Index: 651245 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 1.4788. Min Range: -1.4788

Max Act: 1.2976. Min Act: -0.0001

Data Index: 117157 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 1.4788. Min Range: -1.4788

Max Act: 1.2804. Min Act: -0.0001

Data Index: 554482 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 1.4788. Min Range: -1.4788

Max Act: 1.1868. Min Act: -0.0001

Data Index: 339615 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 1.4788. Min Range: -1.4788

Max Act: 1.2450. Min Act: -0.0001

Data Index: 1289115 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 1.4788. Min Range: -1.4788

Max Act: 1.2565. Min Act: -0.0001

Data Index: 840485 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 1.4788. Min Range: -1.4788

Max Act: 1.2080. Min Act: -0.0001

Data Index: 20897 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 1.4788. Min Range: -1.4788

Max Act: 1.1537. Min Act: -0.0001

Data Index: 390199 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 1.4788. Min Range: -1.4788

Max Act: 1.1867. Min Act: -0.0001

Data Index: 267900 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 1.4788. Min Range: -1.4788

Max Act: 1.1565. Min Act: -0.0001

Data Index: 275545 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 1.4788. Min Range: -1.4788

Max Act: 1.1017. Min Act: -0.0001

Data Index: 577482 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 1.4788. Min Range: -1.4788

Max Act: 1.1403. Min Act: -0.0001

Data Index: 7550 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 1.4788. Min Range: -1.4788

Max Act: 1.1604. Min Act: -0.0001

Data Index: 944374 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 1.4788. Min Range: -1.4788

Max Act: 1.1547. Min Act: -0.0001

Data Index: 1001918 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 1.4788. Min Range: -1.4788

Max Act: 1.1184. Min Act: -0.0001

Data Index: 453678 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 1.4788. Min Range: -1.4788

Max Act: 1.1145. Min Act: -0.0001

Data Index: 303124 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 1.4788. Min Range: -1.4788

Max Act: 1.1447. Min Act: -0.0001

Data Index: 280678 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 1.4788. Min Range: -1.4788

Max Act: 1.1045. Min Act: -0.0001

Data Index: 738180 (C4 (Web Text))

Max Activating Token Index: 590