Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1266 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.6333. Min Act: -0.0001

Data Index: 1252248 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.1682. Min Act: -0.0001

Data Index: 1191958 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 1.6333. Min Range: -1.6333

Max Act: 0.9723. Min Act: -0.0001

Data Index: 94552 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.1438. Min Act: -0.0001

Data Index: 927510 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.1862. Min Act: -0.0001

Data Index: 670875 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 1.6333. Min Range: -1.6333

Max Act: 0.8994. Min Act: -0.0001

Data Index: 1305719 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.0204. Min Act: -0.0001

Data Index: 938320 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.0432. Min Act: -0.0001

Data Index: 43222 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 1.6333. Min Range: -1.6333

Max Act: 0.8179. Min Act: -0.0001

Data Index: 1034 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 1.6333. Min Range: -1.6333

Max Act: 0.8861. Min Act: -0.0001

Data Index: 92717 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 1.6333. Min Range: -1.6333

Max Act: 0.8677. Min Act: -0.0001

Data Index: 385378 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 1.6333. Min Range: -1.6333

Max Act: 0.8165. Min Act: -0.0001

Data Index: 186456 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 1.6333. Min Range: -1.6333

Max Act: 0.8988. Min Act: -0.0001

Data Index: 423623 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 1.6333. Min Range: -1.6333

Max Act: 0.8595. Min Act: -0.0001

Data Index: 826509 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 1.6333. Min Range: -1.6333

Max Act: 0.7734. Min Act: -0.0001

Data Index: 325902 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 1.6333. Min Range: -1.6333

Max Act: 0.7778. Min Act: -0.0001

Data Index: 594489 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 1.6333. Min Range: -1.6333

Max Act: 0.6841. Min Act: -0.0001

Data Index: 181342 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 1.6333. Min Range: -1.6333

Max Act: 0.7403. Min Act: -0.0001

Data Index: 158158 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 1.6333. Min Range: -1.6333

Max Act: 0.6693. Min Act: -0.0001

Data Index: 884382 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 1.6333. Min Range: -1.6333

Max Act: 0.7306. Min Act: -0.0001

Data Index: 548984 (C4 (Web Text))

Max Activating Token Index: 581