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

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

Neuron 2560 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3075. Min Range: -2.3075

Max Act: 2.2435. Min Act: -0.0000

Data Index: 90924 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 2.3075. Min Range: -2.3075

Max Act: 2.3075. Min Act: -0.0000

Data Index: 1219934 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 2.3075. Min Range: -2.3075

Max Act: 2.0661. Min Act: -0.0000

Data Index: 803573 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 2.3075. Min Range: -2.3075

Max Act: 1.8378. Min Act: -0.0000

Data Index: 28788 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 2.3075. Min Range: -2.3075

Max Act: 1.8518. Min Act: -0.0000

Data Index: 1113008 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 2.3075. Min Range: -2.3075

Max Act: 1.5272. Min Act: -0.0000

Data Index: 1187945 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 2.3075. Min Range: -2.3075

Max Act: 1.5910. Min Act: -0.0000

Data Index: 1278407 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 2.3075. Min Range: -2.3075

Max Act: 1.2794. Min Act: -0.0001

Data Index: 485488 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 2.3075. Min Range: -2.3075

Max Act: 1.6090. Min Act: -0.0000

Data Index: 958393 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 2.3075. Min Range: -2.3075

Max Act: 1.4819. Min Act: -0.0000

Data Index: 1044565 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 2.3075. Min Range: -2.3075

Max Act: 1.6471. Min Act: -0.0000

Data Index: 96618 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 2.3075. Min Range: -2.3075

Max Act: 1.5328. Min Act: -0.0000

Data Index: 978351 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 2.3075. Min Range: -2.3075

Max Act: 1.5065. Min Act: -0.0000

Data Index: 367123 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 2.3075. Min Range: -2.3075

Max Act: 1.5017. Min Act: -0.0000

Data Index: 1170448 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 2.3075. Min Range: -2.3075

Max Act: 1.5041. Min Act: -0.0000

Data Index: 624408 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 2.3075. Min Range: -2.3075

Max Act: 1.3977. Min Act: -0.0000

Data Index: 1268394 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 2.3075. Min Range: -2.3075

Max Act: 1.5548. Min Act: -0.0000

Data Index: 1302922 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 2.3075. Min Range: -2.3075

Max Act: 1.4487. Min Act: -0.0000

Data Index: 720175 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 2.3075. Min Range: -2.3075

Max Act: 1.4144. Min Act: -0.0000

Data Index: 589755 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 2.3075. Min Range: -2.3075

Max Act: 1.3245. Min Act: -0.0000

Data Index: 1149350 (C4 (Web Text))

Max Activating Token Index: 951