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

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

Neuron 4076 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.6177. Min Act: -0.0002

Data Index: 1001030 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.6226. Min Act: -0.0002

Data Index: 1101029 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.6508. Min Act: -0.0002

Data Index: 1067029 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.5660. Min Act: -0.0002

Data Index: 1157351 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.5722. Min Act: -0.0002

Data Index: 525229 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.5408. Min Act: -0.0002

Data Index: 36085 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.4798. Min Act: -0.0002

Data Index: 1202055 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.5058. Min Act: -0.0002

Data Index: 221558 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.5425. Min Act: -0.0002

Data Index: 1243156 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.5099. Min Act: -0.0002

Data Index: 1138195 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.4249. Min Act: -0.0002

Data Index: 1058827 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.4178. Min Act: -0.0002

Data Index: 936875 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.3920. Min Act: -0.0002

Data Index: 380939 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.3915. Min Act: -0.0003

Data Index: 234343 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.3995. Min Act: -0.0002

Data Index: 955935 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.4336. Min Act: -0.0002

Data Index: 662915 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.3672. Min Act: -0.0002

Data Index: 607039 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.3632. Min Act: -0.0002

Data Index: 150368 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.4175. Min Act: -0.0002

Data Index: 586388 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.3698. Min Act: -0.0002

Data Index: 860747 (C4 (Web Text))

Max Activating Token Index: 773