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

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

Neuron 5558 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.8422. Min Act: -0.0000

Data Index: 396579 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.7856. Min Act: -0.0000

Data Index: 706186 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6911. Min Act: -0.0000

Data Index: 847535 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.7685. Min Act: -0.0000

Data Index: 1098606 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.8476. Min Act: -0.0000

Data Index: 1296096 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6565. Min Act: 0.0000

Data Index: 631383 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6974. Min Act: -0.0000

Data Index: 1166151 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6132. Min Act: -0.0000

Data Index: 1300899 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6846. Min Act: -0.0000

Data Index: 740036 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6932. Min Act: -0.0000

Data Index: 417204 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6097. Min Act: -0.0000

Data Index: 299062 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6973. Min Act: 0.0000

Data Index: 437276 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1276207 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.7268. Min Act: -0.0000

Data Index: 389276 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6544. Min Act: 0.0000

Data Index: 468013 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1301156 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.7074. Min Act: -0.0000

Data Index: 695013 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.5776. Min Act: 0.0000

Data Index: 783258 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.5701. Min Act: -0.0000

Data Index: 1158034 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6331. Min Act: -0.0000

Data Index: 172207 (C4 (Web Text))

Max Activating Token Index: 745