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

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

Neuron 1284 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.7287. Min Act: -0.0003

Data Index: 659804 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.8316. Min Act: -0.0003

Data Index: 669243 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.7652. Min Act: -0.0003

Data Index: 380074 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6729. Min Act: -0.0003

Data Index: 386091 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6552. Min Act: -0.0003

Data Index: 975848 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6532. Min Act: -0.0003

Data Index: 782963 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6066. Min Act: -0.0003

Data Index: 718123 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5632. Min Act: -0.0004

Data Index: 934059 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6584. Min Act: -0.0003

Data Index: 1021389 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6507. Min Act: -0.0003

Data Index: 559185 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6252. Min Act: -0.0003

Data Index: 378048 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6466. Min Act: -0.0003

Data Index: 627014 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6201. Min Act: -0.0003

Data Index: 357238 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6406. Min Act: -0.0003

Data Index: 235333 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6400. Min Act: -0.0003

Data Index: 547973 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6776. Min Act: -0.0003

Data Index: 619126 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6273. Min Act: -0.0003

Data Index: 1067853 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6285. Min Act: -0.0003

Data Index: 1149029 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6270. Min Act: -0.0003

Data Index: 1026663 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6412. Min Act: -0.0003

Data Index: 716154 (C4 (Web Text))

Max Activating Token Index: 737