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

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

Neuron 1752 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: 0.9365. Min Range: -0.9365

Max Act: 0.9336. Min Act: -0.0001

Data Index: 117156 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.9365. Min Act: -0.0001

Data Index: 1079335 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8284. Min Act: -0.0001

Data Index: 710668 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7203. Min Act: -0.0001

Data Index: 785852 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7927. Min Act: -0.0001

Data Index: 1172541 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8092. Min Act: -0.0001

Data Index: 1335261 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7895. Min Act: -0.0001

Data Index: 830858 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7390. Min Act: -0.0001

Data Index: 1046048 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7023. Min Act: -0.0001

Data Index: 235464 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7185. Min Act: -0.0001

Data Index: 750751 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7389. Min Act: -0.0001

Data Index: 866488 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7095. Min Act: -0.0001

Data Index: 580468 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7237. Min Act: -0.0001

Data Index: 1145941 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6802. Min Act: -0.0001

Data Index: 339336 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6576. Min Act: -0.0001

Data Index: 1145762 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6745. Min Act: -0.0001

Data Index: 347375 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6437. Min Act: -0.0001

Data Index: 310409 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6634. Min Act: -0.0001

Data Index: 85747 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7165. Min Act: -0.0001

Data Index: 600800 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6620. Min Act: -0.0001

Data Index: 271467 (C4 (Web Text))

Max Activating Token Index: 865