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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 90 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.4209. Min Act: -0.0001

Data Index: 758954 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3505. Min Act: -0.0001

Data Index: 317165 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3555. Min Act: -0.0001

Data Index: 990352 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3493. Min Act: -0.0001

Data Index: 1051062 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3213. Min Act: -0.0001

Data Index: 691974 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2982. Min Act: -0.0001

Data Index: 438036 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3347. Min Act: -0.0001

Data Index: 1094444 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3309. Min Act: -0.0001

Data Index: 954626 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3332. Min Act: -0.0001

Data Index: 868939 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2977. Min Act: -0.0001

Data Index: 593938 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3053. Min Act: -0.0001

Data Index: 1315806 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3017. Min Act: -0.0001

Data Index: 69700 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2948. Min Act: -0.0001

Data Index: 10338 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3052. Min Act: -0.0001

Data Index: 729164 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2781. Min Act: -0.0001

Data Index: 89500 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3131. Min Act: -0.0001

Data Index: 328739 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3173. Min Act: -0.0001

Data Index: 1088412 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2922. Min Act: -0.0001

Data Index: 805499 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3020. Min Act: -0.0001

Data Index: 1250301 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2998. Min Act: -0.0001

Data Index: 672391 (C4 (Web Text))

Max Activating Token Index: 237