Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1978 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3405. Min Range: -1.3405

Max Act: 1.3405. Min Act: -0.0000

Data Index: 920685 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 1.3405. Min Range: -1.3405

Max Act: 1.2383. Min Act: -0.0000

Data Index: 228242 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 1.3405. Min Range: -1.3405

Max Act: 1.0172. Min Act: -0.0000

Data Index: 599734 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.9547. Min Act: -0.0000

Data Index: 1303066 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.9262. Min Act: -0.0000

Data Index: 529332 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.9854. Min Act: -0.0000

Data Index: 635630 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.8842. Min Act: -0.0000

Data Index: 567803 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.8228. Min Act: -0.0000

Data Index: 542434 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.8720. Min Act: -0.0000

Data Index: 1330066 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.9259. Min Act: -0.0000

Data Index: 668465 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.8303. Min Act: -0.0000

Data Index: 202355 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.8139. Min Act: -0.0000

Data Index: 543772 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.7885. Min Act: -0.0000

Data Index: 791092 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.8625. Min Act: -0.0000

Data Index: 1246360 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.8119. Min Act: -0.0000

Data Index: 1514731 (Python Code)

Max Activating Token Index: 938

Text #15

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.8207. Min Act: -0.0000

Data Index: 52747 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.8414. Min Act: -0.0000

Data Index: 537420 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.7706. Min Act: -0.0000

Data Index: 1342449 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.7744. Min Act: -0.0000

Data Index: 590971 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.8183. Min Act: -0.0000

Data Index: 496482 (C4 (Web Text))

Max Activating Token Index: 302