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

Dataset: The Pile

Neuron 2853 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: 0.3514. Min Range: -0.3514

Max Act: 0.3257. Min Act: -0.0000

Data Index: 1451561 (The Pile)

Max Activating Token Index: 93

Text #1

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3418. Min Act: -0.0000

Data Index: 204893 (The Pile)

Max Activating Token Index: 249

Text #2

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3514. Min Act: -0.0000

Data Index: 1610616 (The Pile)

Max Activating Token Index: 558

Text #3

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3360. Min Act: -0.0000

Data Index: 526224 (The Pile)

Max Activating Token Index: 146

Text #4

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2995. Min Act: 0.0000

Data Index: 1868547 (The Pile)

Max Activating Token Index: 191

Text #5

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3339. Min Act: -0.0000

Data Index: 835025 (The Pile)

Max Activating Token Index: 689

Text #6

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3263. Min Act: -0.0000

Data Index: 1453501 (The Pile)

Max Activating Token Index: 214

Text #7

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2978. Min Act: -0.0000

Data Index: 189563 (The Pile)

Max Activating Token Index: 428

Text #8

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3332. Min Act: -0.0000

Data Index: 509705 (The Pile)

Max Activating Token Index: 108

Text #9

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3011. Min Act: -0.0000

Data Index: 691951 (The Pile)

Max Activating Token Index: 537

Text #10

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3101. Min Act: -0.0000

Data Index: 265612 (The Pile)

Max Activating Token Index: 741

Text #11

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3067. Min Act: -0.0000

Data Index: 236350 (The Pile)

Max Activating Token Index: 920

Text #12

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2949. Min Act: -0.0000

Data Index: 335671 (The Pile)

Max Activating Token Index: 42

Text #13

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1643458 (The Pile)

Max Activating Token Index: 962

Text #14

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2869. Min Act: -0.0000

Data Index: 301104 (The Pile)

Max Activating Token Index: 727

Text #15

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2665. Min Act: -0.0000

Data Index: 60580 (The Pile)

Max Activating Token Index: 1022

Text #16

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1372646 (The Pile)

Max Activating Token Index: 250

Text #17

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2837. Min Act: 0.0000

Data Index: 249822 (The Pile)

Max Activating Token Index: 175

Text #18

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2750. Min Act: 0.0000

Data Index: 1188187 (The Pile)

Max Activating Token Index: 29

Text #19

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2796. Min Act: -0.0000

Data Index: 293407 (The Pile)

Max Activating Token Index: 475