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

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

Neuron 1965 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: 5.3135. Min Range: -5.3135

Max Act: 5.3135. Min Act: -0.0001

Data Index: 1340221 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 5.3135. Min Range: -5.3135

Max Act: 4.7951. Min Act: -0.0001

Data Index: 816507 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 5.3135. Min Range: -5.3135

Max Act: 4.7944. Min Act: -0.0001

Data Index: 1276585 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 5.3135. Min Range: -5.3135

Max Act: 4.6464. Min Act: -0.0001

Data Index: 147137 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 5.3135. Min Range: -5.3135

Max Act: 4.8230. Min Act: -0.0001

Data Index: 1163849 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 5.3135. Min Range: -5.3135

Max Act: 4.9636. Min Act: -0.0001

Data Index: 1202820 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 5.3135. Min Range: -5.3135

Max Act: 4.9763. Min Act: -0.0001

Data Index: 990294 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 5.3135. Min Range: -5.3135

Max Act: 5.1242. Min Act: -0.0001

Data Index: 1295927 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 5.3135. Min Range: -5.3135

Max Act: 4.9421. Min Act: -0.0001

Data Index: 345229 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 5.3135. Min Range: -5.3135

Max Act: 4.7830. Min Act: -0.0001

Data Index: 415251 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 5.3135. Min Range: -5.3135

Max Act: 4.5771. Min Act: -0.0001

Data Index: 1310425 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 5.3135. Min Range: -5.3135

Max Act: 4.9251. Min Act: -0.0001

Data Index: 586833 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 5.3135. Min Range: -5.3135

Max Act: 4.7470. Min Act: -0.0001

Data Index: 268126 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 5.3135. Min Range: -5.3135

Max Act: 4.4740. Min Act: -0.0001

Data Index: 13502 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 5.3135. Min Range: -5.3135

Max Act: 4.8231. Min Act: -0.0001

Data Index: 1077539 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 5.3135. Min Range: -5.3135

Max Act: 4.8276. Min Act: -0.0001

Data Index: 1283502 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 5.3135. Min Range: -5.3135

Max Act: 4.7965. Min Act: -0.0001

Data Index: 148818 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 5.3135. Min Range: -5.3135

Max Act: 4.8055. Min Act: -0.0001

Data Index: 453373 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 5.3135. Min Range: -5.3135

Max Act: 4.9734. Min Act: -0.0001

Data Index: 774230 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 5.3135. Min Range: -5.3135

Max Act: 4.7877. Min Act: -0.0001

Data Index: 154294 (C4 (Web Text))

Max Activating Token Index: 657