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

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

Neuron 1775 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2998. Min Act: -0.0000

Data Index: 666874 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.3047. Min Act: -0.0000

Data Index: 670301 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.3506. Min Act: -0.0000

Data Index: 345811 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.3221. Min Act: -0.0000

Data Index: 2117 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.3278. Min Act: -0.0000

Data Index: 259036 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.3001. Min Act: -0.0000

Data Index: 526028 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2558. Min Act: -0.0000

Data Index: 84490 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.3163. Min Act: -0.0000

Data Index: 937981 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.3343. Min Act: -0.0000

Data Index: 22864 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2964. Min Act: -0.0000

Data Index: 183483 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2873. Min Act: -0.0000

Data Index: 929600 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.3143. Min Act: -0.0000

Data Index: 414152 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.3043. Min Act: -0.0000

Data Index: 1084767 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.3205. Min Act: -0.0000

Data Index: 326628 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1217337 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2727. Min Act: -0.0000

Data Index: 311247 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.3127. Min Act: -0.0000

Data Index: 132315 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2726. Min Act: -0.0000

Data Index: 1158924 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2866. Min Act: -0.0000

Data Index: 229217 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2784. Min Act: -0.0000

Data Index: 895350 (C4 (Web Text))

Max Activating Token Index: 137