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

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

Neuron 5348 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1167. Min Range: -1.1167

Max Act: 1.1167. Min Act: -0.0001

Data Index: 778224 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 1.1167. Min Range: -1.1167

Max Act: 1.1127. Min Act: -0.0001

Data Index: 18426 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 1.1167. Min Range: -1.1167

Max Act: 1.0346. Min Act: -0.0001

Data Index: 884696 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.9518. Min Act: -0.0001

Data Index: 653121 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.9174. Min Act: -0.0001

Data Index: 785921 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.9562. Min Act: -0.0001

Data Index: 1003947 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.9605. Min Act: -0.0000

Data Index: 1479827 (Python Code)

Max Activating Token Index: 83

Text #7

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.8665. Min Act: -0.0001

Data Index: 544970 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.8195. Min Act: -0.0001

Data Index: 1426835 (Python Code)

Max Activating Token Index: 330

Text #9

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.8741. Min Act: -0.0001

Data Index: 137466 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.8150. Min Act: -0.0001

Data Index: 227952 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.8861. Min Act: -0.0001

Data Index: 1359191 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.9135. Min Act: -0.0001

Data Index: 27832 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.6168. Min Act: -0.0000

Data Index: 1541053 (Python Code)

Max Activating Token Index: 255

Text #14

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.8947. Min Act: -0.0001

Data Index: 799671 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.8442. Min Act: -0.0001

Data Index: 729161 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.8669. Min Act: -0.0001

Data Index: 438934 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.8286. Min Act: -0.0001

Data Index: 388633 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.8500. Min Act: -0.0001

Data Index: 1046707 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.8239. Min Act: -0.0001

Data Index: 272740 (C4 (Web Text))

Max Activating Token Index: 303