Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3174 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3667. Min Act: -0.0000

Data Index: 1214237 (The Pile)

Max Activating Token Index: 763

Text #1

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.3044. Min Act: -0.0000

Data Index: 1378342 (The Pile)

Max Activating Token Index: 472

Text #2

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2809. Min Act: -0.0000

Data Index: 791454 (The Pile)

Max Activating Token Index: 62

Text #3

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2786. Min Act: -0.0000

Data Index: 419574 (The Pile)

Max Activating Token Index: 204

Text #4

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2683. Min Act: -0.0000

Data Index: 293518 (The Pile)

Max Activating Token Index: 242

Text #5

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2266. Min Act: -0.0000

Data Index: 1143418 (The Pile)

Max Activating Token Index: 944

Text #6

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2651. Min Act: -0.0000

Data Index: 1098901 (The Pile)

Max Activating Token Index: 796

Text #7

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2637. Min Act: -0.0000

Data Index: 1151787 (The Pile)

Max Activating Token Index: 6

Text #8

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2274. Min Act: -0.0000

Data Index: 1280929 (The Pile)

Max Activating Token Index: 492

Text #9

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2438. Min Act: -0.0000

Data Index: 1792966 (The Pile)

Max Activating Token Index: 770

Text #10

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2330. Min Act: -0.0000

Data Index: 209663 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1340696 (The Pile)

Max Activating Token Index: 343

Text #12

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2344. Min Act: -0.0000

Data Index: 1505021 (The Pile)

Max Activating Token Index: 385

Text #13

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1117759 (The Pile)

Max Activating Token Index: 838

Text #14

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2195. Min Act: -0.0000

Data Index: 779450 (The Pile)

Max Activating Token Index: 49

Text #15

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2395. Min Act: -0.0000

Data Index: 186837 (The Pile)

Max Activating Token Index: 293

Text #16

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2175. Min Act: -0.0000

Data Index: 1461844 (The Pile)

Max Activating Token Index: 74

Text #17

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2297. Min Act: -0.0000

Data Index: 786160 (The Pile)

Max Activating Token Index: 944

Text #18

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1966970 (The Pile)

Max Activating Token Index: 696

Text #19

Max Range: 0.3667. Min Range: -0.3667

Max Act: 0.2240. Min Act: -0.0000

Data Index: 772651 (The Pile)

Max Activating Token Index: 970