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

Dataset: The Pile

Neuron 2463 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4942. Min Act: -0.0000

Data Index: 1569675 (The Pile)

Max Activating Token Index: 752

Text #1

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4350. Min Act: -0.0000

Data Index: 552226 (The Pile)

Max Activating Token Index: 527

Text #2

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4571. Min Act: -0.0000

Data Index: 1857993 (The Pile)

Max Activating Token Index: 74

Text #3

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4548. Min Act: 0.0000

Data Index: 825049 (The Pile)

Max Activating Token Index: 319

Text #4

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4129. Min Act: -0.0000

Data Index: 965479 (The Pile)

Max Activating Token Index: 321

Text #5

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1286690 (The Pile)

Max Activating Token Index: 440

Text #6

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4361. Min Act: -0.0000

Data Index: 413316 (The Pile)

Max Activating Token Index: 976

Text #7

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4290. Min Act: -0.0000

Data Index: 1810064 (The Pile)

Max Activating Token Index: 349

Text #8

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4260. Min Act: -0.0000

Data Index: 1664525 (The Pile)

Max Activating Token Index: 181

Text #9

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4358. Min Act: -0.0000

Data Index: 225663 (The Pile)

Max Activating Token Index: 415

Text #10

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4049. Min Act: -0.0000

Data Index: 801460 (The Pile)

Max Activating Token Index: 709

Text #11

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4186. Min Act: -0.0000

Data Index: 833759 (The Pile)

Max Activating Token Index: 545

Text #12

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3914. Min Act: -0.0000

Data Index: 540739 (The Pile)

Max Activating Token Index: 71

Text #13

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3918. Min Act: -0.0000

Data Index: 974381 (The Pile)

Max Activating Token Index: 287

Text #14

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4111. Min Act: -0.0000

Data Index: 250970 (The Pile)

Max Activating Token Index: 633

Text #15

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3858. Min Act: -0.0000

Data Index: 1431943 (The Pile)

Max Activating Token Index: 794

Text #16

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3821. Min Act: -0.0000

Data Index: 414000 (The Pile)

Max Activating Token Index: 295

Text #17

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1527413 (The Pile)

Max Activating Token Index: 173

Text #18

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3936. Min Act: -0.0000

Data Index: 438245 (The Pile)

Max Activating Token Index: 269

Text #19

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3845. Min Act: -0.0000

Data Index: 1218987 (The Pile)

Max Activating Token Index: 229