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

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

Neuron 3220 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4772. Min Act: -0.0000

Data Index: 413847 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1146792 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4411. Min Act: -0.0000

Data Index: 130731 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4226. Min Act: -0.0001

Data Index: 301631 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4749. Min Act: -0.0000

Data Index: 1314334 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4280. Min Act: -0.0000

Data Index: 1066485 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4034. Min Act: -0.0000

Data Index: 787132 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3970. Min Act: -0.0000

Data Index: 313662 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3980. Min Act: -0.0000

Data Index: 187530 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4111. Min Act: -0.0000

Data Index: 750074 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4058. Min Act: -0.0000

Data Index: 703031 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4038. Min Act: -0.0001

Data Index: 112866 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4020. Min Act: -0.0000

Data Index: 256497 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4148. Min Act: -0.0000

Data Index: 1335175 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3818. Min Act: -0.0000

Data Index: 812466 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3964. Min Act: -0.0000

Data Index: 269120 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4088. Min Act: -0.0000

Data Index: 605982 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3773. Min Act: -0.0000

Data Index: 352304 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3939. Min Act: -0.0000

Data Index: 504710 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3942. Min Act: -0.0000

Data Index: 1125586 (C4 (Web Text))

Max Activating Token Index: 379