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

Dataset: The Pile

Neuron 2250 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.5164. Min Act: -0.0000

Data Index: 856382 (The Pile)

Max Activating Token Index: 704

Text #1

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.2648. Min Act: -0.0000

Data Index: 1424384 (The Pile)

Max Activating Token Index: 562

Text #2

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.3888. Min Act: -0.0000

Data Index: 338580 (The Pile)

Max Activating Token Index: 690

Text #3

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.3722. Min Act: -0.0000

Data Index: 605320 (The Pile)

Max Activating Token Index: 935

Text #4

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.3695. Min Act: -0.0000

Data Index: 1455025 (The Pile)

Max Activating Token Index: 736

Text #5

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.4077. Min Act: -0.0000

Data Index: 112793 (The Pile)

Max Activating Token Index: 640

Text #6

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.3868. Min Act: -0.0000

Data Index: 1882817 (The Pile)

Max Activating Token Index: 690

Text #7

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.1911. Min Act: -0.0000

Data Index: 1969855 (The Pile)

Max Activating Token Index: 733

Text #8

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.2983. Min Act: -0.0000

Data Index: 207904 (The Pile)

Max Activating Token Index: 882

Text #9

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.2959. Min Act: -0.0000

Data Index: 391396 (The Pile)

Max Activating Token Index: 863

Text #10

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.2946. Min Act: -0.0000

Data Index: 988388 (The Pile)

Max Activating Token Index: 645

Text #11

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.4178. Min Act: -0.0000

Data Index: 354808 (The Pile)

Max Activating Token Index: 502

Text #12

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.2908. Min Act: -0.0000

Data Index: 1009236 (The Pile)

Max Activating Token Index: 575

Text #13

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.2099. Min Act: -0.0000

Data Index: 1936673 (The Pile)

Max Activating Token Index: 375

Text #14

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.2599. Min Act: -0.0000

Data Index: 510327 (The Pile)

Max Activating Token Index: 759

Text #15

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.2431. Min Act: -0.0000

Data Index: 1422650 (The Pile)

Max Activating Token Index: 819

Text #16

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.2184. Min Act: -0.0000

Data Index: 87534 (The Pile)

Max Activating Token Index: 672

Text #17

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.2114. Min Act: -0.0000

Data Index: 185278 (The Pile)

Max Activating Token Index: 654

Text #18

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.2682. Min Act: -0.0000

Data Index: 177784 (The Pile)

Max Activating Token Index: 839

Text #19

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.2384. Min Act: -0.0000

Data Index: 1396119 (The Pile)

Max Activating Token Index: 727