Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3064 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2019. Min Range: -1.2019

Max Act: 1.2019. Min Act: -0.0000

Data Index: 915991 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 1.2019. Min Range: -1.2019

Max Act: 1.1723. Min Act: -0.0000

Data Index: 1127995 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 1.2019. Min Range: -1.2019

Max Act: 1.1471. Min Act: -0.0000

Data Index: 921772 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 1.2019. Min Range: -1.2019

Max Act: 1.1456. Min Act: -0.0000

Data Index: 637095 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 1.2019. Min Range: -1.2019

Max Act: 1.0652. Min Act: -0.0000

Data Index: 736806 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 1.2019. Min Range: -1.2019

Max Act: 1.1071. Min Act: -0.0000

Data Index: 361403 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 1.2019. Min Range: -1.2019

Max Act: 0.9783. Min Act: -0.0000

Data Index: 417199 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 1.2019. Min Range: -1.2019

Max Act: 0.9606. Min Act: -0.0000

Data Index: 650314 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 1.2019. Min Range: -1.2019

Max Act: 0.9976. Min Act: -0.0000

Data Index: 50764 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 1.2019. Min Range: -1.2019

Max Act: 0.9371. Min Act: -0.0000

Data Index: 1340797 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 1.2019. Min Range: -1.2019

Max Act: 0.9533. Min Act: -0.0000

Data Index: 852995 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 1.2019. Min Range: -1.2019

Max Act: 0.9199. Min Act: -0.0000

Data Index: 90667 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 1.2019. Min Range: -1.2019

Max Act: 0.9172. Min Act: -0.0000

Data Index: 1341874 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 1.2019. Min Range: -1.2019

Max Act: 0.9285. Min Act: -0.0000

Data Index: 460584 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 1.2019. Min Range: -1.2019

Max Act: 0.8600. Min Act: -0.0000

Data Index: 1094284 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 1.2019. Min Range: -1.2019

Max Act: 0.8432. Min Act: -0.0000

Data Index: 409288 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 1.2019. Min Range: -1.2019

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1185228 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 1.2019. Min Range: -1.2019

Max Act: 0.8544. Min Act: -0.0000

Data Index: 129557 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 1.2019. Min Range: -1.2019

Max Act: 0.8327. Min Act: -0.0000

Data Index: 748128 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 1.2019. Min Range: -1.2019

Max Act: 0.8563. Min Act: -0.0000

Data Index: 1318423 (C4 (Web Text))

Max Activating Token Index: 908