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

Dataset: The Pile

Neuron 2963 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.3595. Min Act: -0.0000

Data Index: 566858 (The Pile)

Max Activating Token Index: 439

Text #1

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.3282. Min Act: -0.0000

Data Index: 1716068 (The Pile)

Max Activating Token Index: 884

Text #2

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.3622. Min Act: -0.0000

Data Index: 869265 (The Pile)

Max Activating Token Index: 966

Text #3

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.3251. Min Act: -0.0000

Data Index: 466342 (The Pile)

Max Activating Token Index: 103

Text #4

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2666. Min Act: -0.0000

Data Index: 1688581 (The Pile)

Max Activating Token Index: 93

Text #5

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.3184. Min Act: -0.0000

Data Index: 1662435 (The Pile)

Max Activating Token Index: 149

Text #6

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2954. Min Act: -0.0000

Data Index: 1836449 (The Pile)

Max Activating Token Index: 380

Text #7

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2844. Min Act: -0.0000

Data Index: 977008 (The Pile)

Max Activating Token Index: 179

Text #8

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2761. Min Act: -0.0000

Data Index: 1331221 (The Pile)

Max Activating Token Index: 111

Text #9

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2863. Min Act: -0.0000

Data Index: 1077846 (The Pile)

Max Activating Token Index: 152

Text #10

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2781. Min Act: -0.0000

Data Index: 1941745 (The Pile)

Max Activating Token Index: 187

Text #11

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2461. Min Act: -0.0000

Data Index: 1704743 (The Pile)

Max Activating Token Index: 604

Text #12

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.3166. Min Act: -0.0000

Data Index: 314849 (The Pile)

Max Activating Token Index: 301

Text #13

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2669. Min Act: -0.0000

Data Index: 400608 (The Pile)

Max Activating Token Index: 46

Text #14

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2478. Min Act: -0.0000

Data Index: 1044686 (The Pile)

Max Activating Token Index: 386

Text #15

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2605. Min Act: -0.0000

Data Index: 1919613 (The Pile)

Max Activating Token Index: 119

Text #16

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1831280 (The Pile)

Max Activating Token Index: 102

Text #17

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2629. Min Act: -0.0000

Data Index: 150113 (The Pile)

Max Activating Token Index: 322

Text #18

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2758. Min Act: -0.0000

Data Index: 511997 (The Pile)

Max Activating Token Index: 62

Text #19

Max Range: 0.3622. Min Range: -0.3622

Max Act: 0.2755. Min Act: -0.0000

Data Index: 1200777 (The Pile)

Max Activating Token Index: 61