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

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

Neuron 5057 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: 2.1701. Min Range: -2.1701

Max Act: 2.1701. Min Act: -0.0000

Data Index: 1243054 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 2.1701. Min Range: -2.1701

Max Act: 1.7950. Min Act: -0.0000

Data Index: 1221494 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 2.1701. Min Range: -2.1701

Max Act: 1.7818. Min Act: -0.0000

Data Index: 713989 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 2.1701. Min Range: -2.1701

Max Act: 1.8510. Min Act: -0.0000

Data Index: 719642 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 2.1701. Min Range: -2.1701

Max Act: 1.5375. Min Act: -0.0000

Data Index: 14438 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 2.1701. Min Range: -2.1701

Max Act: 1.6243. Min Act: -0.0000

Data Index: 1111202 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 2.1701. Min Range: -2.1701

Max Act: 1.3778. Min Act: -0.0000

Data Index: 238022 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 2.1701. Min Range: -2.1701

Max Act: 1.5429. Min Act: -0.0000

Data Index: 1105849 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 2.1701. Min Range: -2.1701

Max Act: 1.3996. Min Act: -0.0000

Data Index: 7091 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 2.1701. Min Range: -2.1701

Max Act: 1.4004. Min Act: -0.0000

Data Index: 466969 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 2.1701. Min Range: -2.1701

Max Act: 1.5046. Min Act: -0.0000

Data Index: 1219014 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 2.1701. Min Range: -2.1701

Max Act: 1.4663. Min Act: -0.0000

Data Index: 1341676 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 2.1701. Min Range: -2.1701

Max Act: 1.4249. Min Act: -0.0000

Data Index: 331146 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 2.1701. Min Range: -2.1701

Max Act: 1.4048. Min Act: -0.0000

Data Index: 1141753 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 2.1701. Min Range: -2.1701

Max Act: 1.4725. Min Act: -0.0000

Data Index: 495368 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 2.1701. Min Range: -2.1701

Max Act: 1.4577. Min Act: -0.0000

Data Index: 897890 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 2.1701. Min Range: -2.1701

Max Act: 1.3419. Min Act: -0.0000

Data Index: 1219139 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 2.1701. Min Range: -2.1701

Max Act: 1.4763. Min Act: -0.0000

Data Index: 1279344 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 2.1701. Min Range: -2.1701

Max Act: 1.3955. Min Act: -0.0001

Data Index: 430463 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 2.1701. Min Range: -2.1701

Max Act: 1.4337. Min Act: -0.0000

Data Index: 473065 (C4 (Web Text))

Max Activating Token Index: 512