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

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

Neuron 1735 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: 4.8433. Min Range: -4.8433

Max Act: 4.8433. Min Act: -0.0001

Data Index: 507428 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 4.8433. Min Range: -4.8433

Max Act: 4.5117. Min Act: -0.0001

Data Index: 76445 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 4.8433. Min Range: -4.8433

Max Act: 4.1636. Min Act: -0.0001

Data Index: 327096 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 4.8433. Min Range: -4.8433

Max Act: 4.0272. Min Act: -0.0001

Data Index: 1334319 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 4.8433. Min Range: -4.8433

Max Act: 3.6895. Min Act: -0.0001

Data Index: 224624 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 4.8433. Min Range: -4.8433

Max Act: 3.6208. Min Act: -0.0001

Data Index: 1246095 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 4.8433. Min Range: -4.8433

Max Act: 3.4932. Min Act: -0.0001

Data Index: 114681 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 4.8433. Min Range: -4.8433

Max Act: 3.7179. Min Act: -0.0001

Data Index: 1323867 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 4.8433. Min Range: -4.8433

Max Act: 3.6318. Min Act: -0.0001

Data Index: 1209560 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 4.8433. Min Range: -4.8433

Max Act: 3.5445. Min Act: -0.0001

Data Index: 1076602 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 4.8433. Min Range: -4.8433

Max Act: 3.3611. Min Act: -0.0001

Data Index: 155324 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 4.8433. Min Range: -4.8433

Max Act: 3.2635. Min Act: -0.0001

Data Index: 1318279 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 4.8433. Min Range: -4.8433

Max Act: 3.3261. Min Act: -0.0001

Data Index: 287984 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 4.8433. Min Range: -4.8433

Max Act: 3.2779. Min Act: -0.0001

Data Index: 489829 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 4.8433. Min Range: -4.8433

Max Act: 3.2996. Min Act: -0.0001

Data Index: 584618 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 4.8433. Min Range: -4.8433

Max Act: 3.3002. Min Act: -0.0001

Data Index: 282941 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 4.8433. Min Range: -4.8433

Max Act: 3.4168. Min Act: -0.0001

Data Index: 456755 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 4.8433. Min Range: -4.8433

Max Act: 3.4274. Min Act: -0.0001

Data Index: 1009627 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 4.8433. Min Range: -4.8433

Max Act: 3.3519. Min Act: -0.0001

Data Index: 678656 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 4.8433. Min Range: -4.8433

Max Act: 3.3275. Min Act: -0.0001

Data Index: 1187229 (C4 (Web Text))

Max Activating Token Index: 900