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

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

Neuron 4209 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3632. Min Range: -1.3632

Max Act: 1.3632. Min Act: -0.0000

Data Index: 1168374 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 1.3632. Min Range: -1.3632

Max Act: 1.1533. Min Act: -0.0000

Data Index: 1079577 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 1.3632. Min Range: -1.3632

Max Act: 1.0721. Min Act: -0.0000

Data Index: 523667 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 1.3632. Min Range: -1.3632

Max Act: 0.9917. Min Act: -0.0000

Data Index: 852439 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 1.3632. Min Range: -1.3632

Max Act: 1.0491. Min Act: -0.0000

Data Index: 393249 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 1.3632. Min Range: -1.3632

Max Act: 1.0244. Min Act: -0.0000

Data Index: 635630 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 1.3632. Min Range: -1.3632

Max Act: 1.0255. Min Act: -0.0000

Data Index: 788360 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 1.3632. Min Range: -1.3632

Max Act: 0.9484. Min Act: -0.0000

Data Index: 675 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 1.3632. Min Range: -1.3632

Max Act: 1.0043. Min Act: -0.0000

Data Index: 1482424 (Python Code)

Max Activating Token Index: 121

Text #9

Max Range: 1.3632. Min Range: -1.3632

Max Act: 0.9723. Min Act: -0.0000

Data Index: 765911 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 1.3632. Min Range: -1.3632

Max Act: 0.9161. Min Act: -0.0000

Data Index: 1216768 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 1.3632. Min Range: -1.3632

Max Act: 1.0030. Min Act: -0.0000

Data Index: 874198 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 1.3632. Min Range: -1.3632

Max Act: 0.9933. Min Act: -0.0000

Data Index: 538573 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 1.3632. Min Range: -1.3632

Max Act: 0.9043. Min Act: -0.0000

Data Index: 273726 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 1.3632. Min Range: -1.3632

Max Act: 0.9262. Min Act: -0.0000

Data Index: 1579209 (Python Code)

Max Activating Token Index: 738

Text #15

Max Range: 1.3632. Min Range: -1.3632

Max Act: 0.9265. Min Act: -0.0000

Data Index: 1441049 (Python Code)

Max Activating Token Index: 726

Text #16

Max Range: 1.3632. Min Range: -1.3632

Max Act: 1.0070. Min Act: -0.0000

Data Index: 393375 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 1.3632. Min Range: -1.3632

Max Act: 0.9174. Min Act: -0.0000

Data Index: 271777 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 1.3632. Min Range: -1.3632

Max Act: 0.8826. Min Act: -0.0000

Data Index: 642621 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 1.3632. Min Range: -1.3632

Max Act: 0.9415. Min Act: -0.0000

Data Index: 123863 (C4 (Web Text))

Max Activating Token Index: 60