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

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

Neuron 6119 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0946. Min Range: -2.0946

Max Act: 2.0946. Min Act: -0.0000

Data Index: 884172 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 2.0946. Min Range: -2.0946

Max Act: 2.0427. Min Act: -0.0000

Data Index: 452541 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.8648. Min Act: -0.0000

Data Index: 811233 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.8255. Min Act: -0.0000

Data Index: 318050 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.6898. Min Act: -0.0000

Data Index: 1321236 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.6548. Min Act: -0.0000

Data Index: 1299552 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.6555. Min Act: -0.0000

Data Index: 1041585 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.6268. Min Act: -0.0000

Data Index: 240053 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.4339. Min Act: -0.0000

Data Index: 693191 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.5725. Min Act: -0.0000

Data Index: 529629 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.5475. Min Act: -0.0000

Data Index: 890175 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.4361. Min Act: -0.0000

Data Index: 546698 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.4235. Min Act: -0.0000

Data Index: 626354 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.4993. Min Act: -0.0000

Data Index: 1342314 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.4251. Min Act: -0.0000

Data Index: 540956 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.6783. Min Act: -0.0000

Data Index: 51611 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.5004. Min Act: -0.0000

Data Index: 1198853 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.4921. Min Act: -0.0000

Data Index: 1466826 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.3912. Min Act: -0.0000

Data Index: 1307587 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.3952. Min Act: -0.0000

Data Index: 650906 (C4 (Web Text))

Max Activating Token Index: 723