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

Dataset: The Pile

Neuron 4624 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.8705. Min Act: -0.0000

Data Index: 1720637 (The Pile)

Max Activating Token Index: 220

Text #1

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.4419. Min Act: -0.0000

Data Index: 949650 (The Pile)

Max Activating Token Index: 439

Text #2

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.4096. Min Act: -0.0000

Data Index: 358164 (The Pile)

Max Activating Token Index: 281

Text #3

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.3553. Min Act: -0.0000

Data Index: 724071 (The Pile)

Max Activating Token Index: 647

Text #4

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.3152. Min Act: -0.0000

Data Index: 120423 (The Pile)

Max Activating Token Index: 698

Text #5

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.2041. Min Act: -0.0000

Data Index: 1316263 (The Pile)

Max Activating Token Index: 773

Text #6

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.4136. Min Act: -0.0000

Data Index: 1204920 (The Pile)

Max Activating Token Index: 811

Text #7

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.2487. Min Act: -0.0000

Data Index: 831688 (The Pile)

Max Activating Token Index: 692

Text #8

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.1213. Min Act: -0.0000

Data Index: 228323 (The Pile)

Max Activating Token Index: 937

Text #9

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.1734. Min Act: -0.0000

Data Index: 1863286 (The Pile)

Max Activating Token Index: 649

Text #10

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.1705. Min Act: -0.0000

Data Index: 511610 (The Pile)

Max Activating Token Index: 155

Text #11

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.1645. Min Act: -0.0000

Data Index: 982745 (The Pile)

Max Activating Token Index: 715

Text #12

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.1456. Min Act: -0.0000

Data Index: 437581 (The Pile)

Max Activating Token Index: 977

Text #13

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.1947. Min Act: -0.0000

Data Index: 866885 (The Pile)

Max Activating Token Index: 314

Text #14

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.1169. Min Act: -0.0000

Data Index: 1237403 (The Pile)

Max Activating Token Index: 408

Text #15

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.0450. Min Act: 0.0000

Data Index: 409672 (The Pile)

Max Activating Token Index: 902

Text #16

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.0335. Min Act: -0.0000

Data Index: 1596429 (The Pile)

Max Activating Token Index: 902

Text #17

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.1296. Min Act: -0.0000

Data Index: 1614900 (The Pile)

Max Activating Token Index: 997

Text #18

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.0504. Min Act: -0.0000

Data Index: 1488081 (The Pile)

Max Activating Token Index: 936

Text #19

Max Range: 1.8705. Min Range: -1.8705

Max Act: 1.0461. Min Act: -0.0000

Data Index: 1043818 (The Pile)

Max Activating Token Index: 699