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

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

Neuron 2705 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1547. Min Act: -0.0001

Data Index: 863229 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1309. Min Act: -0.0000

Data Index: 1017578 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1129. Min Act: -0.0001

Data Index: 715549 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1039731 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1194. Min Act: -0.0001

Data Index: 615273 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1148. Min Act: -0.0001

Data Index: 1186202 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1147. Min Act: -0.0001

Data Index: 511964 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1142. Min Act: -0.0001

Data Index: 41102 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1086. Min Act: -0.0001

Data Index: 321548 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1112. Min Act: -0.0001

Data Index: 406102 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1120. Min Act: -0.0000

Data Index: 674067 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1093. Min Act: -0.0001

Data Index: 893451 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1083. Min Act: -0.0001

Data Index: 951468 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1004. Min Act: -0.0001

Data Index: 1290336 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1018. Min Act: -0.0001

Data Index: 734586 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.0973. Min Act: -0.0001

Data Index: 1251006 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1033. Min Act: -0.0001

Data Index: 95006 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.0958. Min Act: -0.0001

Data Index: 398961 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.1032. Min Act: -0.0001

Data Index: 1280846 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.1547. Min Range: -0.1547

Max Act: 0.0989. Min Act: -0.0000

Data Index: 831184 (C4 (Web Text))

Max Activating Token Index: 963