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

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

Neuron 3441 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2443. Min Range: -4.2443

Max Act: 4.2443. Min Act: -0.0000

Data Index: 959550 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 4.2443. Min Range: -4.2443

Max Act: 3.1344. Min Act: -0.0000

Data Index: 988026 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 4.2443. Min Range: -4.2443

Max Act: 2.7808. Min Act: -0.0000

Data Index: 126219 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 4.2443. Min Range: -4.2443

Max Act: 2.5016. Min Act: -0.0000

Data Index: 1065300 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 4.2443. Min Range: -4.2443

Max Act: 2.4096. Min Act: -0.0000

Data Index: 413846 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 4.2443. Min Range: -4.2443

Max Act: 2.5101. Min Act: -0.0000

Data Index: 513289 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 4.2443. Min Range: -4.2443

Max Act: 2.5751. Min Act: -0.0000

Data Index: 306290 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 4.2443. Min Range: -4.2443

Max Act: 2.3575. Min Act: -0.0000

Data Index: 85980 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 4.2443. Min Range: -4.2443

Max Act: 2.4144. Min Act: -0.0000

Data Index: 1222720 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 4.2443. Min Range: -4.2443

Max Act: 2.3763. Min Act: -0.0000

Data Index: 166461 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 4.2443. Min Range: -4.2443

Max Act: 2.1175. Min Act: -0.0000

Data Index: 398889 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 4.2443. Min Range: -4.2443

Max Act: 2.2340. Min Act: -0.0000

Data Index: 1195850 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 4.2443. Min Range: -4.2443

Max Act: 2.0681. Min Act: -0.0000

Data Index: 1503802 (Python Code)

Max Activating Token Index: 600

Text #13

Max Range: 4.2443. Min Range: -4.2443

Max Act: 2.1579. Min Act: -0.0000

Data Index: 1054705 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 4.2443. Min Range: -4.2443

Max Act: 2.2750. Min Act: -0.0000

Data Index: 269025 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 4.2443. Min Range: -4.2443

Max Act: 2.0263. Min Act: -0.0000

Data Index: 668164 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 4.2443. Min Range: -4.2443

Max Act: 2.0058. Min Act: -0.0000

Data Index: 103059 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 4.2443. Min Range: -4.2443

Max Act: 2.1038. Min Act: -0.0000

Data Index: 215908 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 4.2443. Min Range: -4.2443

Max Act: 2.0609. Min Act: -0.0000

Data Index: 318106 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 4.2443. Min Range: -4.2443

Max Act: 2.1814. Min Act: -0.0000

Data Index: 1125036 (C4 (Web Text))

Max Activating Token Index: 728