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

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

Neuron 3328 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6784. Min Range: -1.6784

Max Act: 1.5982. Min Act: -0.0001

Data Index: 88130 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 1.6784. Min Range: -1.6784

Max Act: 1.6784. Min Act: -0.0001

Data Index: 1131593 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 1.6784. Min Range: -1.6784

Max Act: 1.6105. Min Act: -0.0001

Data Index: 716121 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 1.6784. Min Range: -1.6784

Max Act: 1.4684. Min Act: -0.0001

Data Index: 840174 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 1.6784. Min Range: -1.6784

Max Act: 1.5115. Min Act: -0.0001

Data Index: 177315 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 1.6784. Min Range: -1.6784

Max Act: 1.3736. Min Act: -0.0001

Data Index: 101455 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 1.6784. Min Range: -1.6784

Max Act: 1.5054. Min Act: -0.0001

Data Index: 1098129 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 1.6784. Min Range: -1.6784

Max Act: 1.5056. Min Act: -0.0001

Data Index: 1089628 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 1.6784. Min Range: -1.6784

Max Act: 1.3098. Min Act: -0.0001

Data Index: 837526 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 1.6784. Min Range: -1.6784

Max Act: 1.4302. Min Act: -0.0001

Data Index: 599256 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 1.6784. Min Range: -1.6784

Max Act: 1.3746. Min Act: -0.0001

Data Index: 636272 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 1.6784. Min Range: -1.6784

Max Act: 1.4394. Min Act: -0.0001

Data Index: 623951 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 1.6784. Min Range: -1.6784

Max Act: 1.3933. Min Act: -0.0001

Data Index: 34365 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 1.6784. Min Range: -1.6784

Max Act: 1.5646. Min Act: -0.0001

Data Index: 468093 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 1.6784. Min Range: -1.6784

Max Act: 1.3306. Min Act: -0.0001

Data Index: 1316585 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 1.6784. Min Range: -1.6784

Max Act: 1.3661. Min Act: -0.0001

Data Index: 1235132 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 1.6784. Min Range: -1.6784

Max Act: 1.2079. Min Act: -0.0001

Data Index: 353353 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 1.6784. Min Range: -1.6784

Max Act: 1.3054. Min Act: -0.0001

Data Index: 240721 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 1.6784. Min Range: -1.6784

Max Act: 1.2730. Min Act: -0.0001

Data Index: 907095 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 1.6784. Min Range: -1.6784

Max Act: 1.3042. Min Act: -0.0001

Data Index: 1299950 (C4 (Web Text))

Max Activating Token Index: 451