Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1716 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1327. Min Act: -0.0001

Data Index: 1068346 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1272560 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1145. Min Act: -0.0001

Data Index: 980006 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1072. Min Act: -0.0001

Data Index: 385668 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1187. Min Act: -0.0001

Data Index: 334739 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0983. Min Act: -0.0001

Data Index: 960840 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0963. Min Act: -0.0001

Data Index: 356890 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0910. Min Act: -0.0001

Data Index: 1105280 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0934. Min Act: -0.0001

Data Index: 796130 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0993. Min Act: -0.0001

Data Index: 166631 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0891. Min Act: -0.0001

Data Index: 794109 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0876. Min Act: -0.0001

Data Index: 1167842 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0835. Min Act: -0.0001

Data Index: 543465 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0869. Min Act: -0.0001

Data Index: 77293 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0852. Min Act: -0.0001

Data Index: 676694 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0837. Min Act: -0.0001

Data Index: 1199885 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0842. Min Act: -0.0001

Data Index: 1079162 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1109914 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0928. Min Act: -0.0001

Data Index: 1065128 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.0903. Min Act: -0.0001

Data Index: 1316375 (C4 (Web Text))

Max Activating Token Index: 33