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

Dataset: The Pile

Neuron 1096 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.1955. Min Act: -0.0000

Data Index: 249615 (The Pile)

Max Activating Token Index: 111

Text #1

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.1535. Min Act: -0.0000

Data Index: 559732 (The Pile)

Max Activating Token Index: 151

Text #2

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.1746. Min Act: -0.0000

Data Index: 1289705 (The Pile)

Max Activating Token Index: 908

Text #3

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.1873. Min Act: -0.0000

Data Index: 1234529 (The Pile)

Max Activating Token Index: 248

Text #4

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.2186. Min Act: -0.0000

Data Index: 108395 (The Pile)

Max Activating Token Index: 304

Text #5

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.1489. Min Act: -0.0000

Data Index: 435244 (The Pile)

Max Activating Token Index: 649

Text #6

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.1242. Min Act: -0.0000

Data Index: 1457349 (The Pile)

Max Activating Token Index: 652

Text #7

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.0950. Min Act: -0.0000

Data Index: 903953 (The Pile)

Max Activating Token Index: 556

Text #8

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.0800. Min Act: -0.0000

Data Index: 838557 (The Pile)

Max Activating Token Index: 296

Text #9

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.0726. Min Act: -0.0000

Data Index: 227189 (The Pile)

Max Activating Token Index: 604

Text #10

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.0343. Min Act: -0.0000

Data Index: 856310 (The Pile)

Max Activating Token Index: 54

Text #11

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.0910. Min Act: -0.0000

Data Index: 346869 (The Pile)

Max Activating Token Index: 62

Text #12

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.0564. Min Act: -0.0000

Data Index: 1340496 (The Pile)

Max Activating Token Index: 403

Text #13

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.0123. Min Act: -0.0000

Data Index: 388945 (The Pile)

Max Activating Token Index: 507

Text #14

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.0104. Min Act: -0.0000

Data Index: 1924247 (The Pile)

Max Activating Token Index: 505

Text #15

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.0089. Min Act: -0.0000

Data Index: 1411473 (The Pile)

Max Activating Token Index: 138

Text #16

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.9287. Min Act: -0.0000

Data Index: 182196 (The Pile)

Max Activating Token Index: 101

Text #17

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.8722. Min Act: -0.0000

Data Index: 242296 (The Pile)

Max Activating Token Index: 862

Text #18

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.9221. Min Act: -0.0000

Data Index: 1162554 (The Pile)

Max Activating Token Index: 909

Text #19

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.0458. Min Act: -0.0000

Data Index: 1778353 (The Pile)

Max Activating Token Index: 304