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

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

Neuron 4204 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: 0.6650. Min Range: -0.6650

Max Act: 0.6650. Min Act: -0.0000

Data Index: 36 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.6084. Min Act: -0.0000

Data Index: 752581 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1170681 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5078. Min Act: -0.0000

Data Index: 1241788 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5096. Min Act: -0.0000

Data Index: 474907 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5408. Min Act: -0.0000

Data Index: 1424693 (Python Code)

Max Activating Token Index: 573

Text #6

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5244. Min Act: -0.0000

Data Index: 713157 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1466129 (Python Code)

Max Activating Token Index: 397

Text #8

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4930. Min Act: -0.0000

Data Index: 693238 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1029903 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5098. Min Act: -0.0000

Data Index: 349198 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4661. Min Act: -0.0000

Data Index: 967954 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4800. Min Act: -0.0000

Data Index: 221195 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1216880 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1488133 (Python Code)

Max Activating Token Index: 605

Text #15

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4959. Min Act: -0.0000

Data Index: 1365904 (Python Code)

Max Activating Token Index: 773

Text #16

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4441. Min Act: -0.0000

Data Index: 52445 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4520. Min Act: -0.0000

Data Index: 976094 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4116. Min Act: -0.0000

Data Index: 311391 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1005056 (C4 (Web Text))

Max Activating Token Index: 691