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

Dataset: The Pile

Neuron 243 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: 1.2530. Min Range: -1.2530

Max Act: 1.2530. Min Act: -0.0000

Data Index: 1293212 (The Pile)

Max Activating Token Index: 524

Text #1

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.8691. Min Act: -0.0000

Data Index: 1363857 (The Pile)

Max Activating Token Index: 583

Text #2

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.0601. Min Act: -0.0000

Data Index: 354928 (The Pile)

Max Activating Token Index: 269

Text #3

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.1538. Min Act: -0.0000

Data Index: 1393308 (The Pile)

Max Activating Token Index: 834

Text #4

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.8164. Min Act: -0.0000

Data Index: 1176857 (The Pile)

Max Activating Token Index: 818

Text #5

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.0607. Min Act: -0.0000

Data Index: 993150 (The Pile)

Max Activating Token Index: 772

Text #6

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.8431. Min Act: -0.0000

Data Index: 1142716 (The Pile)

Max Activating Token Index: 572

Text #7

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.8922. Min Act: -0.0000

Data Index: 127810 (The Pile)

Max Activating Token Index: 177

Text #8

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.0358. Min Act: -0.0000

Data Index: 513105 (The Pile)

Max Activating Token Index: 458

Text #9

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.9356. Min Act: -0.0000

Data Index: 460528 (The Pile)

Max Activating Token Index: 176

Text #10

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.8405. Min Act: -0.0000

Data Index: 710194 (The Pile)

Max Activating Token Index: 206

Text #11

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.8985. Min Act: -0.0000

Data Index: 1107277 (The Pile)

Max Activating Token Index: 555

Text #12

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.9854. Min Act: -0.0000

Data Index: 1175522 (The Pile)

Max Activating Token Index: 782

Text #13

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.8364. Min Act: -0.0000

Data Index: 1068127 (The Pile)

Max Activating Token Index: 20

Text #14

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.9842. Min Act: -0.0000

Data Index: 1783383 (The Pile)

Max Activating Token Index: 938

Text #15

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.8046. Min Act: -0.0000

Data Index: 897792 (The Pile)

Max Activating Token Index: 861

Text #16

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.7237. Min Act: -0.0000

Data Index: 1566886 (The Pile)

Max Activating Token Index: 193

Text #17

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.7262. Min Act: -0.0000

Data Index: 1290804 (The Pile)

Max Activating Token Index: 270

Text #18

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1992389 (The Pile)

Max Activating Token Index: 448

Text #19

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.7550. Min Act: -0.0000

Data Index: 1013434 (The Pile)

Max Activating Token Index: 695