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

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

Neuron 111 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.1577. Min Act: -0.0000

Data Index: 196333 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.3559. Min Act: -0.0000

Data Index: 1344554 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 2.3559. Min Range: -2.3559

Max Act: 2.0309. Min Act: -0.0000

Data Index: 1238866 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 2.3559. Min Range: -2.3559

Max Act: 1.8253. Min Act: -0.0000

Data Index: 564814 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 2.3559. Min Range: -2.3559

Max Act: 1.8179. Min Act: -0.0000

Data Index: 720479 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 2.3559. Min Range: -2.3559

Max Act: 1.9244. Min Act: -0.0000

Data Index: 216180 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 2.3559. Min Range: -2.3559

Max Act: 1.8542. Min Act: -0.0000

Data Index: 654170 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 2.3559. Min Range: -2.3559

Max Act: 1.7298. Min Act: -0.0001

Data Index: 519978 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 2.3559. Min Range: -2.3559

Max Act: 1.8022. Min Act: -0.0000

Data Index: 675406 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 2.3559. Min Range: -2.3559

Max Act: 1.7820. Min Act: -0.0000

Data Index: 1236548 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 2.3559. Min Range: -2.3559

Max Act: 1.7651. Min Act: -0.0000

Data Index: 289499 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 2.3559. Min Range: -2.3559

Max Act: 1.7581. Min Act: -0.0000

Data Index: 1301811 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 2.3559. Min Range: -2.3559

Max Act: 1.8424. Min Act: -0.0000

Data Index: 424097 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 2.3559. Min Range: -2.3559

Max Act: 1.8348. Min Act: -0.0000

Data Index: 944574 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 2.3559. Min Range: -2.3559

Max Act: 1.7030. Min Act: -0.0000

Data Index: 1217944 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 2.3559. Min Range: -2.3559

Max Act: 1.6934. Min Act: -0.0000

Data Index: 1058274 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 2.3559. Min Range: -2.3559

Max Act: 1.6958. Min Act: -0.0000

Data Index: 193014 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 2.3559. Min Range: -2.3559

Max Act: 1.6766. Min Act: -0.0000

Data Index: 214614 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 2.3559. Min Range: -2.3559

Max Act: 1.5847. Min Act: -0.0000

Data Index: 224930 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 2.3559. Min Range: -2.3559

Max Act: 1.6586. Min Act: -0.0000

Data Index: 204439 (C4 (Web Text))

Max Activating Token Index: 28