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

Dataset: The Pile

Neuron 975 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: 0.3374. Min Range: -0.3374

Max Act: 0.3374. Min Act: -0.0000

Data Index: 266194 (The Pile)

Max Activating Token Index: 402

Text #1

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.3131. Min Act: -0.0000

Data Index: 1159723 (The Pile)

Max Activating Token Index: 819

Text #2

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2952. Min Act: -0.0000

Data Index: 1266705 (The Pile)

Max Activating Token Index: 253

Text #3

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1966075 (The Pile)

Max Activating Token Index: 429

Text #4

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2684. Min Act: -0.0000

Data Index: 1964591 (The Pile)

Max Activating Token Index: 354

Text #5

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2621. Min Act: -0.0000

Data Index: 1017210 (The Pile)

Max Activating Token Index: 202

Text #6

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2769. Min Act: -0.0001

Data Index: 1885983 (The Pile)

Max Activating Token Index: 324

Text #7

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2768. Min Act: -0.0000

Data Index: 975144 (The Pile)

Max Activating Token Index: 955

Text #8

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2456. Min Act: -0.0000

Data Index: 377368 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2526. Min Act: -0.0000

Data Index: 1282174 (The Pile)

Max Activating Token Index: 254

Text #10

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1775298 (The Pile)

Max Activating Token Index: 172

Text #11

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2344. Min Act: -0.0000

Data Index: 748024 (The Pile)

Max Activating Token Index: 588

Text #12

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2139. Min Act: -0.0000

Data Index: 385483 (The Pile)

Max Activating Token Index: 877

Text #13

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2241. Min Act: -0.0000

Data Index: 1529296 (The Pile)

Max Activating Token Index: 446

Text #14

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2285. Min Act: 0.0000

Data Index: 349532 (The Pile)

Max Activating Token Index: 497

Text #15

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2061. Min Act: -0.0000

Data Index: 198987 (The Pile)

Max Activating Token Index: 113

Text #16

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2269. Min Act: -0.0000

Data Index: 490275 (The Pile)

Max Activating Token Index: 847

Text #17

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2185. Min Act: -0.0000

Data Index: 796936 (The Pile)

Max Activating Token Index: 750

Text #18

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2191. Min Act: -0.0000

Data Index: 152020 (The Pile)

Max Activating Token Index: 856

Text #19

Max Range: 0.3374. Min Range: -0.3374

Max Act: 0.2175. Min Act: -0.0000

Data Index: 1793791 (The Pile)

Max Activating Token Index: 272