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

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

Neuron 4288 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6469. Min Range: -2.6469

Max Act: 2.6033. Min Act: -0.0000

Data Index: 610955 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 2.6469. Min Range: -2.6469

Max Act: 2.6469. Min Act: -0.0000

Data Index: 971241 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 2.6469. Min Range: -2.6469

Max Act: 2.4339. Min Act: -0.0000

Data Index: 811894 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 2.6469. Min Range: -2.6469

Max Act: 2.2086. Min Act: -0.0000

Data Index: 139996 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 2.6469. Min Range: -2.6469

Max Act: 1.9992. Min Act: -0.0000

Data Index: 966987 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 2.6469. Min Range: -2.6469

Max Act: 1.9526. Min Act: -0.0000

Data Index: 931214 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 2.6469. Min Range: -2.6469

Max Act: 2.0576. Min Act: -0.0000

Data Index: 640238 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 2.6469. Min Range: -2.6469

Max Act: 2.0595. Min Act: -0.0000

Data Index: 690806 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 2.6469. Min Range: -2.6469

Max Act: 2.0438. Min Act: -0.0000

Data Index: 910596 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 2.6469. Min Range: -2.6469

Max Act: 2.1403. Min Act: -0.0000

Data Index: 709513 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 2.6469. Min Range: -2.6469

Max Act: 2.0001. Min Act: -0.0000

Data Index: 1350858 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 2.6469. Min Range: -2.6469

Max Act: 2.1136. Min Act: -0.0000

Data Index: 520120 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 2.6469. Min Range: -2.6469

Max Act: 1.9825. Min Act: -0.0000

Data Index: 320677 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 2.6469. Min Range: -2.6469

Max Act: 1.8734. Min Act: -0.0000

Data Index: 774922 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 2.6469. Min Range: -2.6469

Max Act: 1.9303. Min Act: -0.0000

Data Index: 534810 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 2.6469. Min Range: -2.6469

Max Act: 2.0432. Min Act: -0.0000

Data Index: 154312 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 2.6469. Min Range: -2.6469

Max Act: 1.8816. Min Act: -0.0000

Data Index: 1294890 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 2.6469. Min Range: -2.6469

Max Act: 1.8787. Min Act: 0.0000

Data Index: 115439 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 2.6469. Min Range: -2.6469

Max Act: 1.8878. Min Act: -0.0000

Data Index: 311406 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 2.6469. Min Range: -2.6469

Max Act: 1.9821. Min Act: -0.0000

Data Index: 1180240 (C4 (Web Text))

Max Activating Token Index: 95