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

Dataset: The Pile

Neuron 3984 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: 1.1220. Min Range: -1.1220

Max Act: 1.1220. Min Act: -0.0000

Data Index: 740167 (The Pile)

Max Activating Token Index: 152

Text #1

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.1043. Min Act: -0.0000

Data Index: 568157 (The Pile)

Max Activating Token Index: 699

Text #2

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.0975. Min Act: -0.0000

Data Index: 557608 (The Pile)

Max Activating Token Index: 494

Text #3

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.0493. Min Act: -0.0000

Data Index: 1468570 (The Pile)

Max Activating Token Index: 504

Text #4

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.0160. Min Act: -0.0000

Data Index: 387317 (The Pile)

Max Activating Token Index: 784

Text #5

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.1122. Min Act: -0.0000

Data Index: 1386111 (The Pile)

Max Activating Token Index: 56

Text #6

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.0385. Min Act: -0.0000

Data Index: 778313 (The Pile)

Max Activating Token Index: 551

Text #7

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.0293. Min Act: -0.0000

Data Index: 839743 (The Pile)

Max Activating Token Index: 966

Text #8

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.0338. Min Act: -0.0000

Data Index: 143545 (The Pile)

Max Activating Token Index: 67

Text #9

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9705. Min Act: -0.0000

Data Index: 1365918 (The Pile)

Max Activating Token Index: 32

Text #10

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.0551. Min Act: -0.0000

Data Index: 862858 (The Pile)

Max Activating Token Index: 856

Text #11

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.0530. Min Act: -0.0000

Data Index: 1863422 (The Pile)

Max Activating Token Index: 192

Text #12

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.0621. Min Act: -0.0000

Data Index: 705646 (The Pile)

Max Activating Token Index: 745

Text #13

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.0197. Min Act: -0.0000

Data Index: 1128082 (The Pile)

Max Activating Token Index: 262

Text #14

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9916. Min Act: -0.0000

Data Index: 1919110 (The Pile)

Max Activating Token Index: 367

Text #15

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.0532. Min Act: -0.0000

Data Index: 545171 (The Pile)

Max Activating Token Index: 632

Text #16

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.0501. Min Act: -0.0000

Data Index: 73130 (The Pile)

Max Activating Token Index: 618

Text #17

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.0167. Min Act: -0.0000

Data Index: 1925509 (The Pile)

Max Activating Token Index: 361

Text #18

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.1140. Min Act: -0.0000

Data Index: 426603 (The Pile)

Max Activating Token Index: 581

Text #19

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9947. Min Act: -0.0000

Data Index: 438844 (The Pile)

Max Activating Token Index: 841