Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 661 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.4410. Min Act: -0.0001

Data Index: 868519 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.1695. Min Act: -0.0001

Data Index: 250616 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.2133. Min Act: -0.0001

Data Index: 431977 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.1120. Min Act: -0.0001

Data Index: 137880 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.0768. Min Act: -0.0000

Data Index: 1045635 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.0462. Min Act: -0.0001

Data Index: 1347065 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.1304. Min Act: -0.0001

Data Index: 696719 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.0983. Min Act: -0.0001

Data Index: 532235 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.1324. Min Act: -0.0001

Data Index: 360370 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.2164. Min Act: -0.0001

Data Index: 1242594 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.0888. Min Act: -0.0001

Data Index: 1276583 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 1.4410. Min Range: -1.4410

Max Act: 0.9067. Min Act: -0.0001

Data Index: 137485 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.0246. Min Act: -0.0001

Data Index: 643023 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 1.4410. Min Range: -1.4410

Max Act: 0.9904. Min Act: -0.0001

Data Index: 1259591 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.0512. Min Act: -0.0001

Data Index: 1166755 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 1.4410. Min Range: -1.4410

Max Act: 0.9845. Min Act: -0.0001

Data Index: 401518 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 1.4410. Min Range: -1.4410

Max Act: 0.9641. Min Act: -0.0001

Data Index: 1464394 (Python Code)

Max Activating Token Index: 646

Text #17

Max Range: 1.4410. Min Range: -1.4410

Max Act: 0.9679. Min Act: -0.0001

Data Index: 673221 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.0311. Min Act: -0.0001

Data Index: 997497 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 1.4410. Min Range: -1.4410

Max Act: 0.9635. Min Act: -0.0001

Data Index: 1190073 (C4 (Web Text))

Max Activating Token Index: 384