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

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

Neuron 30 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: 1.0133. Min Range: -1.0133

Max Act: 1.0133. Min Act: -0.0001

Data Index: 886365 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.9622. Min Act: -0.0001

Data Index: 803416 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.9007. Min Act: -0.0001

Data Index: 157183 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.9505. Min Act: -0.0001

Data Index: 143700 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8777. Min Act: -0.0001

Data Index: 133129 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8210. Min Act: -0.0001

Data Index: 126519 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8423. Min Act: -0.0001

Data Index: 281850 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7816. Min Act: -0.0001

Data Index: 1232559 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7982. Min Act: -0.0001

Data Index: 90052 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7753. Min Act: -0.0001

Data Index: 947312 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7351. Min Act: -0.0001

Data Index: 953121 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7556. Min Act: -0.0001

Data Index: 1136234 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7258. Min Act: -0.0001

Data Index: 363984 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.6973. Min Act: -0.0001

Data Index: 501986 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7116. Min Act: -0.0001

Data Index: 1319771 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7303. Min Act: -0.0001

Data Index: 136221 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7145. Min Act: -0.0001

Data Index: 1175102 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7045. Min Act: -0.0001

Data Index: 726379 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7293. Min Act: -0.0001

Data Index: 741282 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7265. Min Act: -0.0001

Data Index: 1123283 (C4 (Web Text))

Max Activating Token Index: 41