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

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

Neuron 4170 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.8382. Min Act: -0.0000

Data Index: 135381 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.9527. Min Act: 0.0000

Data Index: 1033799 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7798. Min Act: -0.0000

Data Index: 1058489 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7856. Min Act: -0.0000

Data Index: 278955 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.8533. Min Act: -0.0000

Data Index: 339430 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.8450. Min Act: -0.0000

Data Index: 747063 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7922. Min Act: -0.0000

Data Index: 1044812 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7879. Min Act: -0.0000

Data Index: 1083602 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7590. Min Act: -0.0000

Data Index: 691420 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7715. Min Act: -0.0000

Data Index: 1102008 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7404. Min Act: -0.0000

Data Index: 1227495 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7602. Min Act: -0.0000

Data Index: 1120234 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7373. Min Act: -0.0000

Data Index: 43286 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7222. Min Act: -0.0000

Data Index: 902068 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7434. Min Act: -0.0000

Data Index: 1085605 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7006. Min Act: -0.0000

Data Index: 947031 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7135. Min Act: -0.0000

Data Index: 472147 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7077. Min Act: -0.0000

Data Index: 103090 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7524. Min Act: -0.0000

Data Index: 1064100 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1046463 (C4 (Web Text))

Max Activating Token Index: 203