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

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

Neuron 4442 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: 1.9045. Min Range: -1.9045

Max Act: 1.9045. Min Act: -0.0000

Data Index: 776469 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 1.9045. Min Range: -1.9045

Max Act: 1.6009. Min Act: -0.0000

Data Index: 1270704 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 1.9045. Min Range: -1.9045

Max Act: 1.4771. Min Act: -0.0000

Data Index: 199474 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 1.9045. Min Range: -1.9045

Max Act: 1.4700. Min Act: -0.0000

Data Index: 378121 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 1.9045. Min Range: -1.9045

Max Act: 1.2604. Min Act: -0.0000

Data Index: 903043 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 1.9045. Min Range: -1.9045

Max Act: 1.2464. Min Act: -0.0000

Data Index: 1043117 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 1.9045. Min Range: -1.9045

Max Act: 1.2476. Min Act: -0.0000

Data Index: 644003 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 1.9045. Min Range: -1.9045

Max Act: 1.2257. Min Act: -0.0000

Data Index: 985093 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 1.9045. Min Range: -1.9045

Max Act: 1.2470. Min Act: -0.0000

Data Index: 959666 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 1.9045. Min Range: -1.9045

Max Act: 1.2263. Min Act: -0.0000

Data Index: 906670 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 1.9045. Min Range: -1.9045

Max Act: 1.2454. Min Act: -0.0000

Data Index: 179955 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 1.9045. Min Range: -1.9045

Max Act: 1.1323. Min Act: -0.0000

Data Index: 186190 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 1.9045. Min Range: -1.9045

Max Act: 1.1936. Min Act: -0.0000

Data Index: 582287 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 1.9045. Min Range: -1.9045

Max Act: 1.0864. Min Act: -0.0000

Data Index: 356085 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 1.9045. Min Range: -1.9045

Max Act: 1.1142. Min Act: -0.0000

Data Index: 614469 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 1.9045. Min Range: -1.9045

Max Act: 1.0665. Min Act: -0.0000

Data Index: 1218658 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 1.9045. Min Range: -1.9045

Max Act: 1.1037. Min Act: -0.0000

Data Index: 837074 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 1.9045. Min Range: -1.9045

Max Act: 1.1501. Min Act: -0.0000

Data Index: 617830 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 1.9045. Min Range: -1.9045

Max Act: 1.1124. Min Act: -0.0000

Data Index: 349409 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 1.9045. Min Range: -1.9045

Max Act: 1.0611. Min Act: -0.0000

Data Index: 717557 (C4 (Web Text))

Max Activating Token Index: 314