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

Dataset: The Pile

Neuron 1900 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: 4.4775. Min Range: -4.4775

Max Act: 4.4775. Min Act: -0.0000

Data Index: 1346569 (The Pile)

Max Activating Token Index: 729

Text #1

Max Range: 4.4775. Min Range: -4.4775

Max Act: 3.9435. Min Act: -0.0000

Data Index: 1196428 (The Pile)

Max Activating Token Index: 358

Text #2

Max Range: 4.4775. Min Range: -4.4775

Max Act: 4.1282. Min Act: -0.0000

Data Index: 1933600 (The Pile)

Max Activating Token Index: 669

Text #3

Max Range: 4.4775. Min Range: -4.4775

Max Act: 3.9380. Min Act: -0.0000

Data Index: 1255050 (The Pile)

Max Activating Token Index: 572

Text #4

Max Range: 4.4775. Min Range: -4.4775

Max Act: 3.5780. Min Act: -0.0000

Data Index: 400555 (The Pile)

Max Activating Token Index: 958

Text #5

Max Range: 4.4775. Min Range: -4.4775

Max Act: 3.8574. Min Act: -0.0000

Data Index: 716712 (The Pile)

Max Activating Token Index: 384

Text #6

Max Range: 4.4775. Min Range: -4.4775

Max Act: 3.7460. Min Act: -0.0000

Data Index: 736422 (The Pile)

Max Activating Token Index: 95

Text #7

Max Range: 4.4775. Min Range: -4.4775

Max Act: 4.0082. Min Act: -0.0000

Data Index: 1072077 (The Pile)

Max Activating Token Index: 962

Text #8

Max Range: 4.4775. Min Range: -4.4775

Max Act: 3.5062. Min Act: -0.0000

Data Index: 1671436 (The Pile)

Max Activating Token Index: 479

Text #9

Max Range: 4.4775. Min Range: -4.4775

Max Act: 3.5221. Min Act: -0.0000

Data Index: 473486 (The Pile)

Max Activating Token Index: 1008

Text #10

Max Range: 4.4775. Min Range: -4.4775

Max Act: 3.4657. Min Act: -0.0000

Data Index: 1379484 (The Pile)

Max Activating Token Index: 177

Text #11

Max Range: 4.4775. Min Range: -4.4775

Max Act: 3.2535. Min Act: -0.0000

Data Index: 955153 (The Pile)

Max Activating Token Index: 697

Text #12

Max Range: 4.4775. Min Range: -4.4775

Max Act: 3.5532. Min Act: -0.0000

Data Index: 508967 (The Pile)

Max Activating Token Index: 458

Text #13

Max Range: 4.4775. Min Range: -4.4775

Max Act: 3.0965. Min Act: -0.0000

Data Index: 293297 (The Pile)

Max Activating Token Index: 603

Text #14

Max Range: 4.4775. Min Range: -4.4775

Max Act: 3.5318. Min Act: -0.0000

Data Index: 1160985 (The Pile)

Max Activating Token Index: 446

Text #15

Max Range: 4.4775. Min Range: -4.4775

Max Act: 3.2299. Min Act: -0.0000

Data Index: 1263771 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 4.4775. Min Range: -4.4775

Max Act: 3.2049. Min Act: -0.0000

Data Index: 1939276 (The Pile)

Max Activating Token Index: 153

Text #17

Max Range: 4.4775. Min Range: -4.4775

Max Act: 3.3237. Min Act: -0.0000

Data Index: 1861495 (The Pile)

Max Activating Token Index: 487

Text #18

Max Range: 4.4775. Min Range: -4.4775

Max Act: 3.3329. Min Act: -0.0000

Data Index: 292836 (The Pile)

Max Activating Token Index: 971

Text #19

Max Range: 4.4775. Min Range: -4.4775

Max Act: 3.6616. Min Act: -0.0000

Data Index: 1982029 (The Pile)

Max Activating Token Index: 833