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

Dataset: The Pile

Neuron 2503 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3538. Min Range: -1.3538

Max Act: 1.3538. Min Act: -0.0000

Data Index: 1398831 (The Pile)

Max Activating Token Index: 768

Text #1

Max Range: 1.3538. Min Range: -1.3538

Max Act: 1.0476. Min Act: -0.0000

Data Index: 1112250 (The Pile)

Max Activating Token Index: 662

Text #2

Max Range: 1.3538. Min Range: -1.3538

Max Act: 1.0933. Min Act: -0.0000

Data Index: 88280 (The Pile)

Max Activating Token Index: 857

Text #3

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.9621. Min Act: -0.0000

Data Index: 1297432 (The Pile)

Max Activating Token Index: 21

Text #4

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.8697. Min Act: -0.0000

Data Index: 1097429 (The Pile)

Max Activating Token Index: 577

Text #5

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.7960. Min Act: -0.0000

Data Index: 1905623 (The Pile)

Max Activating Token Index: 473

Text #6

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.8388. Min Act: -0.0000

Data Index: 1647764 (The Pile)

Max Activating Token Index: 162

Text #7

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.8399. Min Act: -0.0000

Data Index: 1077168 (The Pile)

Max Activating Token Index: 241

Text #8

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.8357. Min Act: -0.0000

Data Index: 1917692 (The Pile)

Max Activating Token Index: 266

Text #9

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1441888 (The Pile)

Max Activating Token Index: 603

Text #10

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.8353. Min Act: -0.0000

Data Index: 1223482 (The Pile)

Max Activating Token Index: 634

Text #11

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1847189 (The Pile)

Max Activating Token Index: 259

Text #12

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.7396. Min Act: -0.0000

Data Index: 236017 (The Pile)

Max Activating Token Index: 629

Text #13

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.7268. Min Act: -0.0000

Data Index: 463070 (The Pile)

Max Activating Token Index: 421

Text #14

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.7889. Min Act: -0.0000

Data Index: 1953540 (The Pile)

Max Activating Token Index: 280

Text #15

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.7321. Min Act: -0.0000

Data Index: 780668 (The Pile)

Max Activating Token Index: 516

Text #16

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.7400. Min Act: -0.0000

Data Index: 13379 (The Pile)

Max Activating Token Index: 707

Text #17

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1282854 (The Pile)

Max Activating Token Index: 61

Text #18

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.7423. Min Act: 0.0000

Data Index: 797943 (The Pile)

Max Activating Token Index: 137

Text #19

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.7371. Min Act: -0.0000

Data Index: 217683 (The Pile)

Max Activating Token Index: 5