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

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

Neuron 2832 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2093. Min Range: -0.2093

Max Act: 0.2093. Min Act: -0.0000

Data Index: 254617 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.2093. Min Range: -0.2093

Max Act: 0.1780. Min Act: -0.0000

Data Index: 1194122 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.2093. Min Range: -0.2093

Max Act: 0.1209. Min Act: -0.0001

Data Index: 88937 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 0.2093. Min Range: -0.2093

Max Act: 0.1296. Min Act: -0.0001

Data Index: 1370802 (Python Code)

Max Activating Token Index: 36

Text #4

Max Range: 0.2093. Min Range: -0.2093

Max Act: 0.1298. Min Act: -0.0001

Data Index: 890059 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.2093. Min Range: -0.2093

Max Act: 0.1324. Min Act: -0.0001

Data Index: 1462692 (Python Code)

Max Activating Token Index: 32

Text #6

Max Range: 0.2093. Min Range: -0.2093

Max Act: 0.1366. Min Act: -0.0000

Data Index: 676540 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 0.2093. Min Range: -0.2093

Max Act: 0.1177. Min Act: -0.0000

Data Index: 761745 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 0.2093. Min Range: -0.2093

Max Act: 0.1199. Min Act: -0.0001

Data Index: 555794 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 0.2093. Min Range: -0.2093

Max Act: 0.1368. Min Act: -0.0000

Data Index: 19568 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.2093. Min Range: -0.2093

Max Act: 0.1128. Min Act: -0.0001

Data Index: 1021761 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.2093. Min Range: -0.2093

Max Act: 0.1293. Min Act: -0.0000

Data Index: 278617 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 0.2093. Min Range: -0.2093

Max Act: 0.1052. Min Act: -0.0001

Data Index: 48936 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.2093. Min Range: -0.2093

Max Act: 0.1309. Min Act: -0.0000

Data Index: 1052058 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.2093. Min Range: -0.2093

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1430517 (Python Code)

Max Activating Token Index: 109

Text #15

Max Range: 0.2093. Min Range: -0.2093

Max Act: 0.1174. Min Act: -0.0001

Data Index: 1099541 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.2093. Min Range: -0.2093

Max Act: 0.1217. Min Act: -0.0001

Data Index: 240809 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 0.2093. Min Range: -0.2093

Max Act: 0.1105. Min Act: -0.0000

Data Index: 475619 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.2093. Min Range: -0.2093

Max Act: 0.0896. Min Act: -0.0001

Data Index: 575298 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 0.2093. Min Range: -0.2093

Max Act: 0.1339. Min Act: -0.0001

Data Index: 336717 (C4 (Web Text))

Max Activating Token Index: 23