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

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

Neuron 2502 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4197. Min Range: -2.4197

Max Act: 2.4197. Min Act: -0.0000

Data Index: 48158 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 2.4197. Min Range: -2.4197

Max Act: 2.1256. Min Act: -0.0000

Data Index: 67009 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 2.4197. Min Range: -2.4197

Max Act: 2.2167. Min Act: -0.0000

Data Index: 977129 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 2.4197. Min Range: -2.4197

Max Act: 2.1519. Min Act: -0.0000

Data Index: 400081 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 2.4197. Min Range: -2.4197

Max Act: 2.2595. Min Act: -0.0000

Data Index: 231634 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 2.4197. Min Range: -2.4197

Max Act: 1.9912. Min Act: -0.0000

Data Index: 961047 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 2.4197. Min Range: -2.4197

Max Act: 1.6284. Min Act: -0.0000

Data Index: 216763 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 2.4197. Min Range: -2.4197

Max Act: 1.8964. Min Act: -0.0000

Data Index: 243859 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 2.4197. Min Range: -2.4197

Max Act: 1.9497. Min Act: -0.0000

Data Index: 879682 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 2.4197. Min Range: -2.4197

Max Act: 1.9091. Min Act: -0.0000

Data Index: 820040 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 2.4197. Min Range: -2.4197

Max Act: 1.5065. Min Act: -0.0000

Data Index: 1184778 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 2.4197. Min Range: -2.4197

Max Act: 1.6646. Min Act: -0.0000

Data Index: 1339202 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 2.4197. Min Range: -2.4197

Max Act: 1.8346. Min Act: -0.0000

Data Index: 978115 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 2.4197. Min Range: -2.4197

Max Act: 1.7027. Min Act: -0.0000

Data Index: 1132348 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 2.4197. Min Range: -2.4197

Max Act: 1.8571. Min Act: -0.0000

Data Index: 865185 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 2.4197. Min Range: -2.4197

Max Act: 1.7291. Min Act: -0.0000

Data Index: 151447 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 2.4197. Min Range: -2.4197

Max Act: 1.6253. Min Act: -0.0000

Data Index: 403597 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 2.4197. Min Range: -2.4197

Max Act: 1.4863. Min Act: -0.0000

Data Index: 302152 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 2.4197. Min Range: -2.4197

Max Act: 1.7143. Min Act: -0.0000

Data Index: 326698 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 2.4197. Min Range: -2.4197

Max Act: 1.5113. Min Act: -0.0000

Data Index: 57442 (C4 (Web Text))

Max Activating Token Index: 730