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

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

Neuron 1573 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: 1.0924. Min Range: -1.0924

Max Act: 1.0924. Min Act: -0.0000

Data Index: 1090846 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 1.0924. Min Range: -1.0924

Max Act: 1.0130. Min Act: -0.0000

Data Index: 170177 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8494. Min Act: -0.0000

Data Index: 1351859 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8471. Min Act: -0.0000

Data Index: 1084803 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8292. Min Act: -0.0000

Data Index: 15229 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.7943. Min Act: -0.0000

Data Index: 236161 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.7236. Min Act: -0.0001

Data Index: 1336188 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8233. Min Act: -0.0000

Data Index: 694623 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.7865. Min Act: -0.0000

Data Index: 271335 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.7139. Min Act: -0.0000

Data Index: 491914 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.6651. Min Act: -0.0000

Data Index: 217174 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.6613. Min Act: -0.0000

Data Index: 292566 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.6484. Min Act: -0.0001

Data Index: 1136886 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.6170. Min Act: -0.0000

Data Index: 979357 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.6555. Min Act: -0.0000

Data Index: 928980 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.6743. Min Act: -0.0001

Data Index: 152234 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.6284. Min Act: -0.0000

Data Index: 900819 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.6341. Min Act: -0.0001

Data Index: 1284464 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.6753. Min Act: -0.0001

Data Index: 620986 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.6106. Min Act: -0.0000

Data Index: 620654 (C4 (Web Text))

Max Activating Token Index: 146