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

Dataset: The Pile

Neuron 1489 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0428. Min Range: -1.0428

Max Act: 1.0428. Min Act: -0.0000

Data Index: 959677 (The Pile)

Max Activating Token Index: 792

Text #1

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.9494. Min Act: -0.0000

Data Index: 1699502 (The Pile)

Max Activating Token Index: 188

Text #2

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.9340. Min Act: -0.0000

Data Index: 1887188 (The Pile)

Max Activating Token Index: 579

Text #3

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.8529. Min Act: -0.0000

Data Index: 804254 (The Pile)

Max Activating Token Index: 241

Text #4

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.8502. Min Act: -0.0000

Data Index: 681819 (The Pile)

Max Activating Token Index: 623

Text #5

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.8789. Min Act: -0.0000

Data Index: 840738 (The Pile)

Max Activating Token Index: 450

Text #6

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7562. Min Act: -0.0000

Data Index: 729294 (The Pile)

Max Activating Token Index: 42

Text #7

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7535. Min Act: -0.0000

Data Index: 269108 (The Pile)

Max Activating Token Index: 59

Text #8

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7916. Min Act: -0.0000

Data Index: 18833 (The Pile)

Max Activating Token Index: 405

Text #9

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.8296. Min Act: -0.0000

Data Index: 280310 (The Pile)

Max Activating Token Index: 137

Text #10

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7680. Min Act: -0.0000

Data Index: 139336 (The Pile)

Max Activating Token Index: 117

Text #11

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7658. Min Act: -0.0000

Data Index: 853033 (The Pile)

Max Activating Token Index: 201

Text #12

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.8027. Min Act: -0.0000

Data Index: 793466 (The Pile)

Max Activating Token Index: 44

Text #13

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.6972. Min Act: -0.0000

Data Index: 1836112 (The Pile)

Max Activating Token Index: 137

Text #14

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7098. Min Act: -0.0000

Data Index: 914706 (The Pile)

Max Activating Token Index: 976

Text #15

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.6842. Min Act: -0.0000

Data Index: 328823 (The Pile)

Max Activating Token Index: 860

Text #16

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7465. Min Act: -0.0000

Data Index: 829869 (The Pile)

Max Activating Token Index: 1022

Text #17

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7116. Min Act: -0.0000

Data Index: 449536 (The Pile)

Max Activating Token Index: 932

Text #18

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1023835 (The Pile)

Max Activating Token Index: 919

Text #19

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.6940. Min Act: -0.0000

Data Index: 1518126 (The Pile)

Max Activating Token Index: 1011