Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4965 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.8175. Min Act: -0.0000

Data Index: 227875 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.2550. Min Act: -0.0000

Data Index: 1157081 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.3151. Min Act: -0.0000

Data Index: 746092 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.3211. Min Act: -0.0000

Data Index: 457195 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 3.8175. Min Range: -3.8175

Max Act: 2.9920. Min Act: -0.0000

Data Index: 166123 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.2112. Min Act: -0.0000

Data Index: 797068 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.3747. Min Act: -0.0000

Data Index: 360573 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.0259. Min Act: -0.0000

Data Index: 151087 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.0245. Min Act: -0.0000

Data Index: 1067990 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.1555. Min Act: -0.0000

Data Index: 690868 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.0106. Min Act: -0.0000

Data Index: 1071911 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.1457. Min Act: -0.0000

Data Index: 210284 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.0808. Min Act: -0.0000

Data Index: 956685 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.0104. Min Act: -0.0000

Data Index: 243838 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 3.8175. Min Range: -3.8175

Max Act: 2.9967. Min Act: -0.0000

Data Index: 868408 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.0674. Min Act: -0.0000

Data Index: 888391 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 3.8175. Min Range: -3.8175

Max Act: 2.9783. Min Act: -0.0000

Data Index: 751933 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 3.8175. Min Range: -3.8175

Max Act: 2.9554. Min Act: -0.0000

Data Index: 970584 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 3.8175. Min Range: -3.8175

Max Act: 2.9603. Min Act: -0.0000

Data Index: 1246507 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 3.8175. Min Range: -3.8175

Max Act: 2.8055. Min Act: -0.0000

Data Index: 237130 (C4 (Web Text))

Max Activating Token Index: 133