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

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

Neuron 3098 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7394. Min Range: -2.7394

Max Act: 2.7394. Min Act: -0.0000

Data Index: 797607 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 2.7394. Min Range: -2.7394

Max Act: 2.4041. Min Act: -0.0000

Data Index: 422436 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 2.7394. Min Range: -2.7394

Max Act: 2.1976. Min Act: -0.0000

Data Index: 154595 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 2.7394. Min Range: -2.7394

Max Act: 2.1963. Min Act: -0.0000

Data Index: 281208 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 2.7394. Min Range: -2.7394

Max Act: 1.9883. Min Act: -0.0000

Data Index: 858024 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 2.7394. Min Range: -2.7394

Max Act: 1.9145. Min Act: -0.0000

Data Index: 213013 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 2.7394. Min Range: -2.7394

Max Act: 1.8147. Min Act: -0.0000

Data Index: 1031076 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 2.7394. Min Range: -2.7394

Max Act: 1.9170. Min Act: -0.0000

Data Index: 1011546 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 2.7394. Min Range: -2.7394

Max Act: 1.6870. Min Act: -0.0000

Data Index: 575399 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 2.7394. Min Range: -2.7394

Max Act: 1.7348. Min Act: 0.0001

Data Index: 604220 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 2.7394. Min Range: -2.7394

Max Act: 1.7399. Min Act: 0.0001

Data Index: 1167185 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 2.7394. Min Range: -2.7394

Max Act: 1.6357. Min Act: 0.0001

Data Index: 511622 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 2.7394. Min Range: -2.7394

Max Act: 1.6901. Min Act: 0.0000

Data Index: 558162 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 2.7394. Min Range: -2.7394

Max Act: 1.5908. Min Act: -0.0000

Data Index: 599329 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 2.7394. Min Range: -2.7394

Max Act: 1.6593. Min Act: -0.0000

Data Index: 318089 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 2.7394. Min Range: -2.7394

Max Act: 1.5433. Min Act: -0.0000

Data Index: 945248 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 2.7394. Min Range: -2.7394

Max Act: 1.6094. Min Act: -0.0000

Data Index: 475065 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 2.7394. Min Range: -2.7394

Max Act: 1.5953. Min Act: 0.0001

Data Index: 974918 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 2.7394. Min Range: -2.7394

Max Act: 1.5948. Min Act: 0.0000

Data Index: 1149507 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 2.7394. Min Range: -2.7394

Max Act: 1.6753. Min Act: -0.0000

Data Index: 494753 (C4 (Web Text))

Max Activating Token Index: 473