Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2402 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2931. Min Act: 0.0000

Data Index: 1054594 (The Pile)

Max Activating Token Index: 473

Text #1

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1848900 (The Pile)

Max Activating Token Index: 185

Text #2

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2788. Min Act: -0.0000

Data Index: 361230 (The Pile)

Max Activating Token Index: 483

Text #3

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2739. Min Act: -0.0000

Data Index: 237061 (The Pile)

Max Activating Token Index: 926

Text #4

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1723525 (The Pile)

Max Activating Token Index: 864

Text #5

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2655. Min Act: -0.0000

Data Index: 848978 (The Pile)

Max Activating Token Index: 518

Text #6

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2506. Min Act: -0.0000

Data Index: 812443 (The Pile)

Max Activating Token Index: 287

Text #7

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2658. Min Act: -0.0000

Data Index: 18087 (The Pile)

Max Activating Token Index: 351

Text #8

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2522. Min Act: -0.0000

Data Index: 816816 (The Pile)

Max Activating Token Index: 815

Text #9

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2528. Min Act: -0.0000

Data Index: 807193 (The Pile)

Max Activating Token Index: 629

Text #10

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2506. Min Act: -0.0000

Data Index: 1353123 (The Pile)

Max Activating Token Index: 439

Text #11

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2511. Min Act: -0.0000

Data Index: 1902126 (The Pile)

Max Activating Token Index: 259

Text #12

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1296024 (The Pile)

Max Activating Token Index: 553

Text #13

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2465. Min Act: -0.0000

Data Index: 338674 (The Pile)

Max Activating Token Index: 1003

Text #14

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2453. Min Act: -0.0000

Data Index: 315872 (The Pile)

Max Activating Token Index: 213

Text #15

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2467. Min Act: -0.0000

Data Index: 1102115 (The Pile)

Max Activating Token Index: 265

Text #16

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2364. Min Act: -0.0000

Data Index: 331944 (The Pile)

Max Activating Token Index: 318

Text #17

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2362. Min Act: -0.0000

Data Index: 333600 (The Pile)

Max Activating Token Index: 400

Text #18

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2438. Min Act: -0.0000

Data Index: 1865484 (The Pile)

Max Activating Token Index: 147

Text #19

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2421. Min Act: -0.0000

Data Index: 1752570 (The Pile)

Max Activating Token Index: 279