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

Dataset: The Pile

Neuron 1000 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: 1.2446. Min Range: -1.2446

Max Act: 1.2446. Min Act: 0.0000

Data Index: 1050892 (The Pile)

Max Activating Token Index: 192

Text #1

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0272. Min Act: -0.0000

Data Index: 81153 (The Pile)

Max Activating Token Index: 901

Text #2

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9920. Min Act: -0.0000

Data Index: 471082 (The Pile)

Max Activating Token Index: 887

Text #3

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0390. Min Act: 0.0000

Data Index: 1195190 (The Pile)

Max Activating Token Index: 581

Text #4

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9988. Min Act: -0.0000

Data Index: 531531 (The Pile)

Max Activating Token Index: 280

Text #5

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9174. Min Act: -0.0000

Data Index: 1625963 (The Pile)

Max Activating Token Index: 819

Text #6

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9484. Min Act: -0.0000

Data Index: 242245 (The Pile)

Max Activating Token Index: 428

Text #7

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.8967. Min Act: 0.0000

Data Index: 1164845 (The Pile)

Max Activating Token Index: 369

Text #8

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.8239. Min Act: -0.0000

Data Index: 466903 (The Pile)

Max Activating Token Index: 792

Text #9

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9626. Min Act: -0.0000

Data Index: 1150072 (The Pile)

Max Activating Token Index: 433

Text #10

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0031. Min Act: -0.0000

Data Index: 1640639 (The Pile)

Max Activating Token Index: 667

Text #11

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9174. Min Act: -0.0000

Data Index: 565616 (The Pile)

Max Activating Token Index: 139

Text #12

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.8529. Min Act: 0.0000

Data Index: 114752 (The Pile)

Max Activating Token Index: 151

Text #13

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.8095. Min Act: -0.0000

Data Index: 1426339 (The Pile)

Max Activating Token Index: 83

Text #14

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.8339. Min Act: -0.0000

Data Index: 1125640 (The Pile)

Max Activating Token Index: 845

Text #15

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.7424. Min Act: 0.0000

Data Index: 110643 (The Pile)

Max Activating Token Index: 250

Text #16

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.7995. Min Act: -0.0000

Data Index: 345380 (The Pile)

Max Activating Token Index: 184

Text #17

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.8407. Min Act: 0.0000

Data Index: 1577430 (The Pile)

Max Activating Token Index: 1019

Text #18

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.7997. Min Act: -0.0000

Data Index: 1157491 (The Pile)

Max Activating Token Index: 254

Text #19

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.7925. Min Act: -0.0000

Data Index: 1263927 (The Pile)

Max Activating Token Index: 787