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

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

Neuron 404 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: 1.7139. Min Range: -1.7139

Max Act: 1.7139. Min Act: -0.0001

Data Index: 296118 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.7070. Min Act: -0.0001

Data Index: 144198 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.5692. Min Act: -0.0001

Data Index: 854241 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.4788. Min Act: -0.0001

Data Index: 438540 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.4759. Min Act: -0.0001

Data Index: 359931 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.4344. Min Act: -0.0001

Data Index: 285914 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.3959. Min Act: -0.0001

Data Index: 830946 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.3848. Min Act: -0.0001

Data Index: 727566 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.4348. Min Act: -0.0001

Data Index: 765275 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.3776. Min Act: -0.0001

Data Index: 159127 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.3747. Min Act: -0.0001

Data Index: 181763 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.3392. Min Act: -0.0001

Data Index: 1234240 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.2860. Min Act: -0.0001

Data Index: 419151 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.2860. Min Act: -0.0001

Data Index: 1084649 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.2361. Min Act: -0.0001

Data Index: 1149563 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.3831. Min Act: -0.0001

Data Index: 1030927 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.1879. Min Act: -0.0001

Data Index: 120994 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.2168. Min Act: -0.0001

Data Index: 549841 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.2621. Min Act: -0.0001

Data Index: 868407 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.2123. Min Act: -0.0001

Data Index: 547532 (C4 (Web Text))

Max Activating Token Index: 384