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

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

Neuron 3640 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.7654. Min Act: -0.0001

Data Index: 855602 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.7317. Min Act: -0.0001

Data Index: 53459 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.6918. Min Act: -0.0001

Data Index: 600996 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.7216. Min Act: -0.0001

Data Index: 706634 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.7088. Min Act: -0.0001

Data Index: 921222 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.6273. Min Act: -0.0000

Data Index: 449012 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.6400. Min Act: -0.0000

Data Index: 663435 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.6318. Min Act: -0.0001

Data Index: 1301989 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5991. Min Act: -0.0000

Data Index: 366012 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.6143. Min Act: -0.0001

Data Index: 708047 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.6100. Min Act: -0.0000

Data Index: 154471 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5883. Min Act: -0.0000

Data Index: 416421 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1329281 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5550. Min Act: -0.0000

Data Index: 646562 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5461. Min Act: -0.0001

Data Index: 642753 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.4991. Min Act: -0.0001

Data Index: 623506 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5250. Min Act: -0.0000

Data Index: 113155 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1150319 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5394. Min Act: -0.0001

Data Index: 381504 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5096. Min Act: -0.0000

Data Index: 436590 (C4 (Web Text))

Max Activating Token Index: 92