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

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

Neuron 1103 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: 0.8530. Min Range: -0.8530

Max Act: 0.8530. Min Act: -0.0001

Data Index: 782207 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.7639. Min Act: -0.0001

Data Index: 625940 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.7380. Min Act: -0.0001

Data Index: 817158 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.7007. Min Act: -0.0001

Data Index: 91437 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6781. Min Act: -0.0001

Data Index: 1137320 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6908. Min Act: -0.0001

Data Index: 1165351 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6587. Min Act: -0.0001

Data Index: 1090854 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6490. Min Act: -0.0001

Data Index: 1222048 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6515. Min Act: -0.0001

Data Index: 681715 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6797. Min Act: -0.0001

Data Index: 925162 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6788. Min Act: -0.0001

Data Index: 6104 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6389. Min Act: -0.0001

Data Index: 31188 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6473. Min Act: -0.0001

Data Index: 876485 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6277. Min Act: -0.0001

Data Index: 1228000 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6267. Min Act: -0.0001

Data Index: 1205304 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6381. Min Act: -0.0001

Data Index: 87244 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6669. Min Act: -0.0001

Data Index: 1018080 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6467. Min Act: -0.0001

Data Index: 1318484 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6223. Min Act: -0.0001

Data Index: 1121145 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.5968. Min Act: -0.0001

Data Index: 381393 (C4 (Web Text))

Max Activating Token Index: 901