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

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

Neuron 925 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.6311. Min Act: -0.0000

Data Index: 137987 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5657. Min Act: -0.0000

Data Index: 938573 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5618. Min Act: -0.0000

Data Index: 399099 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5919. Min Act: -0.0000

Data Index: 406374 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5656. Min Act: -0.0000

Data Index: 1081135 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1256802 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5030. Min Act: -0.0000

Data Index: 583622 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5369. Min Act: -0.0000

Data Index: 381996 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5296. Min Act: -0.0000

Data Index: 564565 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5454. Min Act: -0.0000

Data Index: 1187065 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5396. Min Act: -0.0000

Data Index: 763279 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4434. Min Act: -0.0000

Data Index: 562772 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4712. Min Act: -0.0000

Data Index: 424399 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4559. Min Act: -0.0000

Data Index: 306948 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1045102 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4568. Min Act: -0.0000

Data Index: 659909 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4239. Min Act: -0.0000

Data Index: 236107 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4500. Min Act: -0.0000

Data Index: 564646 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4471. Min Act: -0.0000

Data Index: 281802 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4328. Min Act: -0.0000

Data Index: 952089 (C4 (Web Text))

Max Activating Token Index: 859