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

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

Neuron 2368 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4346. Min Range: -1.4346

Max Act: 1.4337. Min Act: -0.0001

Data Index: 216126 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 1.4346. Min Range: -1.4346

Max Act: 1.2931. Min Act: -0.0001

Data Index: 1136972 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 1.4346. Min Range: -1.4346

Max Act: 1.4346. Min Act: -0.0001

Data Index: 566923 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 1.4346. Min Range: -1.4346

Max Act: 1.3280. Min Act: -0.0001

Data Index: 972781 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 1.4346. Min Range: -1.4346

Max Act: 1.3984. Min Act: -0.0001

Data Index: 873075 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 1.4346. Min Range: -1.4346

Max Act: 1.3323. Min Act: -0.0001

Data Index: 428896 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 1.4346. Min Range: -1.4346

Max Act: 1.1132. Min Act: -0.0001

Data Index: 847371 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 1.4346. Min Range: -1.4346

Max Act: 0.9332. Min Act: -0.0001

Data Index: 305542 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 1.4346. Min Range: -1.4346

Max Act: 0.9855. Min Act: -0.0001

Data Index: 703450 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 1.4346. Min Range: -1.4346

Max Act: 1.1189. Min Act: -0.0001

Data Index: 820274 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 1.4346. Min Range: -1.4346

Max Act: 1.0069. Min Act: -0.0001

Data Index: 392168 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 1.4346. Min Range: -1.4346

Max Act: 0.9995. Min Act: -0.0001

Data Index: 589949 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 1.4346. Min Range: -1.4346

Max Act: 0.8015. Min Act: -0.0001

Data Index: 615470 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 1.4346. Min Range: -1.4346

Max Act: 1.0396. Min Act: -0.0001

Data Index: 186567 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 1.4346. Min Range: -1.4346

Max Act: 1.0317. Min Act: -0.0001

Data Index: 522331 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 1.4346. Min Range: -1.4346

Max Act: 0.9503. Min Act: -0.0001

Data Index: 1281238 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 1.4346. Min Range: -1.4346

Max Act: 0.8708. Min Act: -0.0001

Data Index: 595619 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 1.4346. Min Range: -1.4346

Max Act: 0.9856. Min Act: -0.0001

Data Index: 1117891 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 1.4346. Min Range: -1.4346

Max Act: 1.1695. Min Act: -0.0001

Data Index: 1166946 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 1.4346. Min Range: -1.4346

Max Act: 0.9440. Min Act: -0.0001

Data Index: 360148 (C4 (Web Text))

Max Activating Token Index: 475