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

Dataset: The Pile

Neuron 441 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.3306. Min Act: -0.0000

Data Index: 1626102 (The Pile)

Max Activating Token Index: 726

Text #1

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.4179. Min Act: -0.0000

Data Index: 469997 (The Pile)

Max Activating Token Index: 1003

Text #2

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.3240. Min Act: -0.0000

Data Index: 1407231 (The Pile)

Max Activating Token Index: 457

Text #3

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.3015. Min Act: -0.0000

Data Index: 767098 (The Pile)

Max Activating Token Index: 671

Text #4

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.2810. Min Act: -0.0000

Data Index: 1377485 (The Pile)

Max Activating Token Index: 1009

Text #5

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.2437. Min Act: -0.0000

Data Index: 565880 (The Pile)

Max Activating Token Index: 847

Text #6

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.2850. Min Act: -0.0000

Data Index: 1074969 (The Pile)

Max Activating Token Index: 936

Text #7

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.2110. Min Act: -0.0000

Data Index: 428572 (The Pile)

Max Activating Token Index: 620

Text #8

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.1554. Min Act: -0.0000

Data Index: 1900109 (The Pile)

Max Activating Token Index: 764

Text #9

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.2959. Min Act: -0.0000

Data Index: 1832042 (The Pile)

Max Activating Token Index: 589

Text #10

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.1520. Min Act: -0.0000

Data Index: 985640 (The Pile)

Max Activating Token Index: 186

Text #11

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.2411. Min Act: -0.0000

Data Index: 763929 (The Pile)

Max Activating Token Index: 218

Text #12

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.2112. Min Act: -0.0000

Data Index: 391037 (The Pile)

Max Activating Token Index: 938

Text #13

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.2132. Min Act: -0.0000

Data Index: 253891 (The Pile)

Max Activating Token Index: 817

Text #14

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.1782. Min Act: -0.0000

Data Index: 9097 (The Pile)

Max Activating Token Index: 541

Text #15

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.7372. Min Act: -0.0000

Data Index: 257704 (The Pile)

Max Activating Token Index: 637

Text #16

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.1708. Min Act: -0.0000

Data Index: 536276 (The Pile)

Max Activating Token Index: 278

Text #17

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.1714. Min Act: -0.0000

Data Index: 422038 (The Pile)

Max Activating Token Index: 187

Text #18

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.2024. Min Act: -0.0000

Data Index: 1318853 (The Pile)

Max Activating Token Index: 595

Text #19

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.1583. Min Act: -0.0000

Data Index: 72206 (The Pile)

Max Activating Token Index: 915