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

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

Neuron 1298 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4806. Min Act: -0.0000

Data Index: 1131060 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4705. Min Act: -0.0001

Data Index: 463830 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4637. Min Act: -0.0001

Data Index: 1352582 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4582. Min Act: -0.0001

Data Index: 99506 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4331. Min Act: -0.0001

Data Index: 1186477 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4191. Min Act: -0.0001

Data Index: 846217 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4610. Min Act: -0.0000

Data Index: 254509 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1046237 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3828. Min Act: -0.0000

Data Index: 193005 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3916. Min Act: -0.0000

Data Index: 1105584 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4102. Min Act: -0.0000

Data Index: 932164 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3975. Min Act: -0.0001

Data Index: 1247502 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4446. Min Act: -0.0000

Data Index: 255302 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1077742 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3532. Min Act: -0.0000

Data Index: 1204052 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3637. Min Act: -0.0001

Data Index: 143421 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3552. Min Act: -0.0001

Data Index: 1075389 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3444. Min Act: -0.0001

Data Index: 556630 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3553. Min Act: -0.0001

Data Index: 304468 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3349. Min Act: -0.0001

Data Index: 167485 (C4 (Web Text))

Max Activating Token Index: 234