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

Dataset: The Pile

Neuron 163 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: 0.9059. Min Range: -0.9059

Max Act: 0.8577. Min Act: -0.0000

Data Index: 959897 (The Pile)

Max Activating Token Index: 984

Text #1

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8284. Min Act: -0.0000

Data Index: 360008 (The Pile)

Max Activating Token Index: 872

Text #2

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.9059. Min Act: -0.0000

Data Index: 1352854 (The Pile)

Max Activating Token Index: 677

Text #3

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1039189 (The Pile)

Max Activating Token Index: 949

Text #4

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8168. Min Act: -0.0000

Data Index: 924279 (The Pile)

Max Activating Token Index: 984

Text #5

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8402. Min Act: -0.0000

Data Index: 979143 (The Pile)

Max Activating Token Index: 757

Text #6

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8877. Min Act: -0.0000

Data Index: 978782 (The Pile)

Max Activating Token Index: 899

Text #7

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1525354 (The Pile)

Max Activating Token Index: 334

Text #8

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6898. Min Act: -0.0000

Data Index: 1480007 (The Pile)

Max Activating Token Index: 305

Text #9

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6948. Min Act: -0.0000

Data Index: 1080020 (The Pile)

Max Activating Token Index: 363

Text #10

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1783087 (The Pile)

Max Activating Token Index: 237

Text #11

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.3904. Min Act: -0.0000

Data Index: 1309128 (The Pile)

Max Activating Token Index: 179

Text #12

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.3692. Min Act: -0.0000

Data Index: 905898 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.3338. Min Act: -0.0000

Data Index: 253918 (The Pile)

Max Activating Token Index: 377

Text #14

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.3011. Min Act: -0.0000

Data Index: 564987 (The Pile)

Max Activating Token Index: 134

Text #15

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.3219. Min Act: -0.0000

Data Index: 414520 (The Pile)

Max Activating Token Index: 582

Text #16

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.2784. Min Act: -0.0000

Data Index: 843326 (The Pile)

Max Activating Token Index: 999

Text #17

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.3026. Min Act: -0.0000

Data Index: 1079298 (The Pile)

Max Activating Token Index: 433

Text #18

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.2885. Min Act: -0.0000

Data Index: 117207 (The Pile)

Max Activating Token Index: 751

Text #19

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.3099. Min Act: -0.0000

Data Index: 1906320 (The Pile)

Max Activating Token Index: 624