Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 592 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.8270. Min Act: -0.0000

Data Index: 1339623 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.5196. Min Act: -0.0000

Data Index: 146476 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.3248. Min Act: -0.0000

Data Index: 401110 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.3262. Min Act: -0.0000

Data Index: 1047573 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.3050. Min Act: -0.0000

Data Index: 1321985 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.2280. Min Act: -0.0000

Data Index: 312808 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.3135. Min Act: -0.0000

Data Index: 974697 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.2953. Min Act: -0.0000

Data Index: 262316 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.1653. Min Act: -0.0000

Data Index: 555417 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.1076. Min Act: -0.0000

Data Index: 1042656 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.0885. Min Act: -0.0000

Data Index: 743092 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.0676. Min Act: -0.0000

Data Index: 897824 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.0614. Min Act: -0.0000

Data Index: 1299704 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.1539. Min Act: -0.0000

Data Index: 743279 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.0200. Min Act: -0.0000

Data Index: 811610 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 2.8270. Min Range: -2.8270

Max Act: 1.8976. Min Act: -0.0000

Data Index: 771310 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 2.8270. Min Range: -2.8270

Max Act: 1.9013. Min Act: -0.0000

Data Index: 686675 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 2.8270. Min Range: -2.8270

Max Act: 2.0688. Min Act: -0.0000

Data Index: 478389 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 2.8270. Min Range: -2.8270

Max Act: 1.9677. Min Act: -0.0000

Data Index: 359787 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 2.8270. Min Range: -2.8270

Max Act: 1.9568. Min Act: -0.0000

Data Index: 1063244 (C4 (Web Text))

Max Activating Token Index: 714