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

Dataset: The Pile

Neuron 1970 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: 0.3213. Min Range: -0.3213

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1651663 (The Pile)

Max Activating Token Index: 929

Text #1

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2917. Min Act: -0.0000

Data Index: 675057 (The Pile)

Max Activating Token Index: 718

Text #2

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2818. Min Act: -0.0000

Data Index: 1673984 (The Pile)

Max Activating Token Index: 621

Text #3

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2543. Min Act: -0.0000

Data Index: 1936024 (The Pile)

Max Activating Token Index: 682

Text #4

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2447. Min Act: -0.0000

Data Index: 404229 (The Pile)

Max Activating Token Index: 751

Text #5

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2382. Min Act: -0.0000

Data Index: 447528 (The Pile)

Max Activating Token Index: 98

Text #6

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2291. Min Act: -0.0000

Data Index: 629884 (The Pile)

Max Activating Token Index: 74

Text #7

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2514. Min Act: -0.0000

Data Index: 1132350 (The Pile)

Max Activating Token Index: 625

Text #8

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2689. Min Act: -0.0000

Data Index: 1980134 (The Pile)

Max Activating Token Index: 873

Text #9

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2531. Min Act: -0.0000

Data Index: 1212107 (The Pile)

Max Activating Token Index: 972

Text #10

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1798671 (The Pile)

Max Activating Token Index: 481

Text #11

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2322. Min Act: -0.0000

Data Index: 751418 (The Pile)

Max Activating Token Index: 483

Text #12

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2335. Min Act: -0.0000

Data Index: 1371181 (The Pile)

Max Activating Token Index: 453

Text #13

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2373. Min Act: -0.0000

Data Index: 654573 (The Pile)

Max Activating Token Index: 91

Text #14

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2276. Min Act: -0.0000

Data Index: 110738 (The Pile)

Max Activating Token Index: 422

Text #15

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2196. Min Act: -0.0000

Data Index: 751234 (The Pile)

Max Activating Token Index: 507

Text #16

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2139. Min Act: -0.0000

Data Index: 793285 (The Pile)

Max Activating Token Index: 207

Text #17

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1797197 (The Pile)

Max Activating Token Index: 553

Text #18

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2284. Min Act: -0.0000

Data Index: 1586444 (The Pile)

Max Activating Token Index: 140

Text #19

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2146. Min Act: -0.0000

Data Index: 253865 (The Pile)

Max Activating Token Index: 423