Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2822 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.4492. Min Act: -0.0000

Data Index: 331994 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3676. Min Act: -0.0000

Data Index: 402537 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3380. Min Act: -0.0000

Data Index: 1024324 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3082. Min Act: -0.0000

Data Index: 788034 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1023315 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2734. Min Act: -0.0000

Data Index: 877749 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2693. Min Act: -0.0000

Data Index: 303551 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2741. Min Act: -0.0000

Data Index: 1119443 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2476. Min Act: -0.0000

Data Index: 746966 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2648. Min Act: -0.0000

Data Index: 909002 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2607. Min Act: -0.0000

Data Index: 270439 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2272. Min Act: -0.0000

Data Index: 258989 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2371. Min Act: -0.0000

Data Index: 239703 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2602. Min Act: -0.0000

Data Index: 624918 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1136750 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2329. Min Act: -0.0000

Data Index: 203596 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2213. Min Act: -0.0000

Data Index: 491735 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2186. Min Act: -0.0000

Data Index: 490585 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1230050 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2114. Min Act: -0.0000

Data Index: 1108159 (C4 (Web Text))

Max Activating Token Index: 367