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

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

Neuron 2534 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.7539. Min Act: -0.0001

Data Index: 1090838 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.3326. Min Act: -0.0001

Data Index: 377288 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.3080. Min Act: -0.0001

Data Index: 466198 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.4241. Min Act: -0.0001

Data Index: 180087 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.3895. Min Act: -0.0001

Data Index: 700293 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.4649. Min Act: -0.0001

Data Index: 1021806 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.2728. Min Act: -0.0001

Data Index: 742201 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.3053. Min Act: -0.0001

Data Index: 58079 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.2539. Min Act: -0.0001

Data Index: 723195 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.3025. Min Act: -0.0001

Data Index: 702837 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.2611. Min Act: -0.0001

Data Index: 243033 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.3198. Min Act: -0.0001

Data Index: 1078840 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.2411. Min Act: -0.0001

Data Index: 722628 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.2065. Min Act: -0.0001

Data Index: 209211 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.2379. Min Act: -0.0001

Data Index: 245325 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.2664. Min Act: -0.0001

Data Index: 1218379 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.2179. Min Act: -0.0001

Data Index: 223692 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.2497. Min Act: -0.0001

Data Index: 106653 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.1757. Min Act: -0.0001

Data Index: 738895 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.2143. Min Act: -0.0001

Data Index: 202591 (C4 (Web Text))

Max Activating Token Index: 890