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

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

Neuron 4087 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.9066. Min Act: -0.0001

Data Index: 708235 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.8927. Min Act: -0.0001

Data Index: 828946 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.7835. Min Act: -0.0001

Data Index: 476156 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.7297. Min Act: -0.0001

Data Index: 1125062 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.7241. Min Act: -0.0001

Data Index: 1314054 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.7033. Min Act: -0.0001

Data Index: 966397 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6915. Min Act: -0.0001

Data Index: 86948 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6922. Min Act: -0.0001

Data Index: 1323913 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6514. Min Act: -0.0001

Data Index: 941071 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.5940. Min Act: -0.0001

Data Index: 1136474 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6400. Min Act: -0.0001

Data Index: 227524 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6771. Min Act: -0.0001

Data Index: 1233175 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6423. Min Act: -0.0001

Data Index: 462289 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6409. Min Act: -0.0001

Data Index: 225940 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6142. Min Act: -0.0001

Data Index: 696596 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6296. Min Act: -0.0001

Data Index: 1343870 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.5701. Min Act: -0.0001

Data Index: 238869 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.5793. Min Act: -0.0001

Data Index: 674089 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6046. Min Act: -0.0001

Data Index: 199375 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.5820. Min Act: -0.0001

Data Index: 864436 (C4 (Web Text))

Max Activating Token Index: 827