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

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

Neuron 339 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0605. Min Range: -3.0605

Max Act: 3.0605. Min Act: -0.0001

Data Index: 1214545 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 3.0605. Min Range: -3.0605

Max Act: 3.0463. Min Act: -0.0001

Data Index: 601245 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 3.0605. Min Range: -3.0605

Max Act: 3.0205. Min Act: -0.0001

Data Index: 373125 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 3.0605. Min Range: -3.0605

Max Act: 3.0579. Min Act: -0.0001

Data Index: 655777 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 3.0605. Min Range: -3.0605

Max Act: 2.7324. Min Act: -0.0001

Data Index: 806261 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 3.0605. Min Range: -3.0605

Max Act: 2.4274. Min Act: -0.0001

Data Index: 921280 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 3.0605. Min Range: -3.0605

Max Act: 2.6300. Min Act: -0.0001

Data Index: 1193100 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 3.0605. Min Range: -3.0605

Max Act: 2.6118. Min Act: -0.0001

Data Index: 1356341 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 3.0605. Min Range: -3.0605

Max Act: 2.8167. Min Act: -0.0001

Data Index: 559739 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 3.0605. Min Range: -3.0605

Max Act: 2.6670. Min Act: -0.0001

Data Index: 546580 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 3.0605. Min Range: -3.0605

Max Act: 2.5367. Min Act: -0.0001

Data Index: 1217070 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 3.0605. Min Range: -3.0605

Max Act: 2.4155. Min Act: -0.0001

Data Index: 346023 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 3.0605. Min Range: -3.0605

Max Act: 2.4844. Min Act: -0.0001

Data Index: 963150 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 3.0605. Min Range: -3.0605

Max Act: 2.4895. Min Act: -0.0001

Data Index: 159445 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 3.0605. Min Range: -3.0605

Max Act: 2.4633. Min Act: -0.0001

Data Index: 1182887 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 3.0605. Min Range: -3.0605

Max Act: 2.4512. Min Act: -0.0001

Data Index: 964916 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 3.0605. Min Range: -3.0605

Max Act: 2.6905. Min Act: -0.0001

Data Index: 334688 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 3.0605. Min Range: -3.0605

Max Act: 2.3105. Min Act: -0.0001

Data Index: 1255630 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 3.0605. Min Range: -3.0605

Max Act: 2.5389. Min Act: -0.0001

Data Index: 369286 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 3.0605. Min Range: -3.0605

Max Act: 2.4130. Min Act: -0.0001

Data Index: 684200 (C4 (Web Text))

Max Activating Token Index: 21