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

Dataset: The Pile

Neuron 3711 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: 0.3276. Min Range: -0.3276

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1521583 (The Pile)

Max Activating Token Index: 794

Text #1

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1782253 (The Pile)

Max Activating Token Index: 801

Text #2

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2809. Min Act: -0.0000

Data Index: 711901 (The Pile)

Max Activating Token Index: 539

Text #3

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2161. Min Act: -0.0000

Data Index: 1699342 (The Pile)

Max Activating Token Index: 839

Text #4

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2608. Min Act: -0.0000

Data Index: 703110 (The Pile)

Max Activating Token Index: 756

Text #5

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2472. Min Act: -0.0000

Data Index: 62602 (The Pile)

Max Activating Token Index: 784

Text #6

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2185. Min Act: -0.0000

Data Index: 1569778 (The Pile)

Max Activating Token Index: 758

Text #7

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1061673 (The Pile)

Max Activating Token Index: 715

Text #8

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2009. Min Act: -0.0000

Data Index: 1076794 (The Pile)

Max Activating Token Index: 570

Text #9

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2533. Min Act: -0.0000

Data Index: 855046 (The Pile)

Max Activating Token Index: 801

Text #10

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1892216 (The Pile)

Max Activating Token Index: 681

Text #11

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2195. Min Act: -0.0000

Data Index: 1998352 (The Pile)

Max Activating Token Index: 472

Text #12

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.3149. Min Act: -0.0000

Data Index: 836649 (The Pile)

Max Activating Token Index: 114

Text #13

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2303. Min Act: -0.0000

Data Index: 736491 (The Pile)

Max Activating Token Index: 206

Text #14

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2524. Min Act: -0.0000

Data Index: 1405894 (The Pile)

Max Activating Token Index: 496

Text #15

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2686. Min Act: -0.0000

Data Index: 1797439 (The Pile)

Max Activating Token Index: 435

Text #16

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2340. Min Act: -0.0000

Data Index: 1917062 (The Pile)

Max Activating Token Index: 816

Text #17

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2287. Min Act: -0.0000

Data Index: 1569581 (The Pile)

Max Activating Token Index: 589

Text #18

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2419. Min Act: -0.0000

Data Index: 420525 (The Pile)

Max Activating Token Index: 985

Text #19

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2392. Min Act: -0.0000

Data Index: 1847235 (The Pile)

Max Activating Token Index: 311