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

Dataset: The Pile

Neuron 3884 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: 1.2656. Min Range: -1.2656

Max Act: 1.2656. Min Act: -0.0000

Data Index: 222131 (The Pile)

Max Activating Token Index: 1008

Text #1

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.1683. Min Act: -0.0000

Data Index: 708759 (The Pile)

Max Activating Token Index: 969

Text #2

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.1344. Min Act: -0.0000

Data Index: 995056 (The Pile)

Max Activating Token Index: 921

Text #3

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.1228. Min Act: -0.0000

Data Index: 1542947 (The Pile)

Max Activating Token Index: 221

Text #4

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.0559. Min Act: -0.0000

Data Index: 112392 (The Pile)

Max Activating Token Index: 105

Text #5

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.1271. Min Act: -0.0000

Data Index: 1677169 (The Pile)

Max Activating Token Index: 314

Text #6

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.1344. Min Act: -0.0000

Data Index: 790532 (The Pile)

Max Activating Token Index: 673

Text #7

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.1292. Min Act: -0.0000

Data Index: 1266005 (The Pile)

Max Activating Token Index: 72

Text #8

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.9201. Min Act: -0.0000

Data Index: 1870251 (The Pile)

Max Activating Token Index: 433

Text #9

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.0504. Min Act: -0.0000

Data Index: 1129352 (The Pile)

Max Activating Token Index: 882

Text #10

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.0464. Min Act: -0.0000

Data Index: 1375808 (The Pile)

Max Activating Token Index: 238

Text #11

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.0799. Min Act: -0.0000

Data Index: 1979647 (The Pile)

Max Activating Token Index: 1021

Text #12

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.9974. Min Act: -0.0000

Data Index: 104563 (The Pile)

Max Activating Token Index: 488

Text #13

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.0240. Min Act: -0.0000

Data Index: 394075 (The Pile)

Max Activating Token Index: 453

Text #14

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.9794. Min Act: -0.0000

Data Index: 260169 (The Pile)

Max Activating Token Index: 23

Text #15

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.9754. Min Act: -0.0000

Data Index: 371412 (The Pile)

Max Activating Token Index: 50

Text #16

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.0160. Min Act: -0.0000

Data Index: 995042 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.9255. Min Act: -0.0000

Data Index: 1389333 (The Pile)

Max Activating Token Index: 357

Text #18

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.8572. Min Act: 0.0000

Data Index: 1154935 (The Pile)

Max Activating Token Index: 526

Text #19

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.9453. Min Act: 0.0000

Data Index: 424085 (The Pile)

Max Activating Token Index: 430