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

Dataset: The Pile

Neuron 2903 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: 1.9070. Min Range: -1.9070

Max Act: 1.9070. Min Act: -0.0000

Data Index: 695153 (The Pile)

Max Activating Token Index: 449

Text #1

Max Range: 1.9070. Min Range: -1.9070

Max Act: 1.6013. Min Act: -0.0000

Data Index: 1144700 (The Pile)

Max Activating Token Index: 626

Text #2

Max Range: 1.9070. Min Range: -1.9070

Max Act: 1.3646. Min Act: -0.0000

Data Index: 476914 (The Pile)

Max Activating Token Index: 610

Text #3

Max Range: 1.9070. Min Range: -1.9070

Max Act: 1.2151. Min Act: -0.0000

Data Index: 465736 (The Pile)

Max Activating Token Index: 583

Text #4

Max Range: 1.9070. Min Range: -1.9070

Max Act: 1.3180. Min Act: -0.0000

Data Index: 1227170 (The Pile)

Max Activating Token Index: 182

Text #5

Max Range: 1.9070. Min Range: -1.9070

Max Act: 1.2775. Min Act: -0.0000

Data Index: 762551 (The Pile)

Max Activating Token Index: 260

Text #6

Max Range: 1.9070. Min Range: -1.9070

Max Act: 1.2151. Min Act: -0.0000

Data Index: 466004 (The Pile)

Max Activating Token Index: 264

Text #7

Max Range: 1.9070. Min Range: -1.9070

Max Act: 1.1727. Min Act: -0.0000

Data Index: 835763 (The Pile)

Max Activating Token Index: 259

Text #8

Max Range: 1.9070. Min Range: -1.9070

Max Act: 1.2424. Min Act: -0.0000

Data Index: 437303 (The Pile)

Max Activating Token Index: 833

Text #9

Max Range: 1.9070. Min Range: -1.9070

Max Act: 1.2474. Min Act: -0.0000

Data Index: 1053610 (The Pile)

Max Activating Token Index: 267

Text #10

Max Range: 1.9070. Min Range: -1.9070

Max Act: 1.1270. Min Act: -0.0000

Data Index: 1219225 (The Pile)

Max Activating Token Index: 655

Text #11

Max Range: 1.9070. Min Range: -1.9070

Max Act: 1.1412. Min Act: -0.0000

Data Index: 438880 (The Pile)

Max Activating Token Index: 483

Text #12

Max Range: 1.9070. Min Range: -1.9070

Max Act: 1.0757. Min Act: -0.0000

Data Index: 755578 (The Pile)

Max Activating Token Index: 743

Text #13

Max Range: 1.9070. Min Range: -1.9070

Max Act: 1.0272. Min Act: -0.0000

Data Index: 1203558 (The Pile)

Max Activating Token Index: 543

Text #14

Max Range: 1.9070. Min Range: -1.9070

Max Act: 1.0358. Min Act: -0.0000

Data Index: 1464927 (The Pile)

Max Activating Token Index: 518

Text #15

Max Range: 1.9070. Min Range: -1.9070

Max Act: 1.0701. Min Act: -0.0000

Data Index: 1210852 (The Pile)

Max Activating Token Index: 721

Text #16

Max Range: 1.9070. Min Range: -1.9070

Max Act: 0.9934. Min Act: -0.0000

Data Index: 1347379 (The Pile)

Max Activating Token Index: 443

Text #17

Max Range: 1.9070. Min Range: -1.9070

Max Act: 1.0348. Min Act: -0.0000

Data Index: 940433 (The Pile)

Max Activating Token Index: 155

Text #18

Max Range: 1.9070. Min Range: -1.9070

Max Act: 1.0293. Min Act: -0.0000

Data Index: 139375 (The Pile)

Max Activating Token Index: 591

Text #19

Max Range: 1.9070. Min Range: -1.9070

Max Act: 0.9839. Min Act: -0.0000

Data Index: 1211259 (The Pile)

Max Activating Token Index: 879