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

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

Neuron 3317 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.4962. Min Act: -0.0001

Data Index: 460604 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.4005. Min Act: -0.0001

Data Index: 502905 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.3923. Min Act: -0.0001

Data Index: 1190632 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.1883. Min Act: -0.0001

Data Index: 610431 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.0855. Min Act: -0.0001

Data Index: 1297220 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.1307. Min Act: -0.0001

Data Index: 458939 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 1.4962. Min Range: -1.4962

Max Act: 0.9889. Min Act: -0.0001

Data Index: 1289325 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.0415. Min Act: -0.0001

Data Index: 729172 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 1.4962. Min Range: -1.4962

Max Act: 0.9475. Min Act: -0.0001

Data Index: 611838 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 1.4962. Min Range: -1.4962

Max Act: 0.7813. Min Act: -0.0001

Data Index: 1006746 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 1.4962. Min Range: -1.4962

Max Act: 0.9328. Min Act: -0.0001

Data Index: 1228310 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 1.4962. Min Range: -1.4962

Max Act: 0.9826. Min Act: -0.0001

Data Index: 183475 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 1.4962. Min Range: -1.4962

Max Act: 0.8976. Min Act: -0.0001

Data Index: 1157246 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 1.4962. Min Range: -1.4962

Max Act: 0.8687. Min Act: -0.0001

Data Index: 615618 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 1.4962. Min Range: -1.4962

Max Act: 0.8496. Min Act: -0.0001

Data Index: 193051 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 1.4962. Min Range: -1.4962

Max Act: 0.9427. Min Act: -0.0001

Data Index: 21776 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 1.4962. Min Range: -1.4962

Max Act: 0.8123. Min Act: -0.0001

Data Index: 705922 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 1.4962. Min Range: -1.4962

Max Act: 0.8059. Min Act: -0.0001

Data Index: 325261 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 1.4962. Min Range: -1.4962

Max Act: 0.7523. Min Act: -0.0001

Data Index: 229379 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 1.4962. Min Range: -1.4962

Max Act: 0.7958. Min Act: -0.0001

Data Index: 106898 (C4 (Web Text))

Max Activating Token Index: 886