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

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

Neuron 1334 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: 1.2287. Min Range: -1.2287

Max Act: 1.1620. Min Act: -0.0001

Data Index: 1015623 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 1.2287. Min Range: -1.2287

Max Act: 1.2287. Min Act: -0.0001

Data Index: 166031 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 1.2287. Min Range: -1.2287

Max Act: 1.2155. Min Act: -0.0001

Data Index: 387838 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 1.2287. Min Range: -1.2287

Max Act: 1.0553. Min Act: -0.0001

Data Index: 1277001 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 1.2287. Min Range: -1.2287

Max Act: 1.0238. Min Act: -0.0001

Data Index: 1353925 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 1.2287. Min Range: -1.2287

Max Act: 1.0435. Min Act: -0.0001

Data Index: 299599 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 1.2287. Min Range: -1.2287

Max Act: 1.0181. Min Act: -0.0001

Data Index: 74006 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.9377. Min Act: -0.0001

Data Index: 32499 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.9798. Min Act: -0.0001

Data Index: 369291 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.9776. Min Act: -0.0001

Data Index: 1268285 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.9424. Min Act: -0.0001

Data Index: 1243692 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 1.2287. Min Range: -1.2287

Max Act: 1.0209. Min Act: -0.0001

Data Index: 1343089 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.9940. Min Act: -0.0001

Data Index: 222604 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.9577. Min Act: -0.0001

Data Index: 61005 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.9804. Min Act: -0.0001

Data Index: 101884 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.9183. Min Act: -0.0001

Data Index: 1327932 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.9671. Min Act: -0.0001

Data Index: 175614 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.9934. Min Act: -0.0001

Data Index: 969471 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.9850. Min Act: -0.0001

Data Index: 268935 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.9851. Min Act: -0.0001

Data Index: 788385 (C4 (Web Text))

Max Activating Token Index: 433