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

Dataset: The Pile

Neuron 2350 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.8252. Min Act: -0.0000

Data Index: 576821 (The Pile)

Max Activating Token Index: 418

Text #1

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.8123. Min Act: -0.0000

Data Index: 8391 (The Pile)

Max Activating Token Index: 739

Text #2

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.8084. Min Act: -0.0000

Data Index: 99904 (The Pile)

Max Activating Token Index: 333

Text #3

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.8024. Min Act: -0.0000

Data Index: 274455 (The Pile)

Max Activating Token Index: 276

Text #4

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.7464. Min Act: -0.0000

Data Index: 305109 (The Pile)

Max Activating Token Index: 526

Text #5

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6947. Min Act: -0.0000

Data Index: 1026767 (The Pile)

Max Activating Token Index: 45

Text #6

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5914. Min Act: -0.0000

Data Index: 289008 (The Pile)

Max Activating Token Index: 214

Text #7

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.7474. Min Act: -0.0000

Data Index: 1051382 (The Pile)

Max Activating Token Index: 18

Text #8

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5420. Min Act: -0.0000

Data Index: 984803 (The Pile)

Max Activating Token Index: 617

Text #9

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5171. Min Act: -0.0000

Data Index: 480917 (The Pile)

Max Activating Token Index: 921

Text #10

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6360. Min Act: -0.0000

Data Index: 769307 (The Pile)

Max Activating Token Index: 585

Text #11

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1203823 (The Pile)

Max Activating Token Index: 549

Text #12

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5774. Min Act: -0.0000

Data Index: 1318724 (The Pile)

Max Activating Token Index: 477

Text #13

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5385. Min Act: -0.0000

Data Index: 1969777 (The Pile)

Max Activating Token Index: 318

Text #14

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5244. Min Act: -0.0000

Data Index: 619201 (The Pile)

Max Activating Token Index: 73

Text #15

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5412. Min Act: -0.0000

Data Index: 681419 (The Pile)

Max Activating Token Index: 633

Text #16

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6540. Min Act: -0.0000

Data Index: 847066 (The Pile)

Max Activating Token Index: 813

Text #17

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5307. Min Act: -0.0000

Data Index: 876949 (The Pile)

Max Activating Token Index: 315

Text #18

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1896745 (The Pile)

Max Activating Token Index: 217

Text #19

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.4623. Min Act: -0.0000

Data Index: 852146 (The Pile)

Max Activating Token Index: 70