Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 354 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.4319. Min Act: -0.0001

Data Index: 704274 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.4008. Min Act: -0.0001

Data Index: 79998 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3419. Min Act: -0.0001

Data Index: 492088 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3535. Min Act: -0.0001

Data Index: 1015415 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3126. Min Act: -0.0001

Data Index: 1320725 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.2784. Min Act: -0.0001

Data Index: 1042527 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3411. Min Act: -0.0001

Data Index: 1294015 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3408. Min Act: -0.0001

Data Index: 187416 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3175. Min Act: -0.0001

Data Index: 1184606 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3337. Min Act: -0.0001

Data Index: 68714 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3150. Min Act: -0.0001

Data Index: 1254824 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3001. Min Act: -0.0001

Data Index: 747625 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3306. Min Act: -0.0001

Data Index: 130212 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3066. Min Act: -0.0001

Data Index: 315822 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3181. Min Act: -0.0001

Data Index: 341111 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3129. Min Act: -0.0001

Data Index: 554255 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3067. Min Act: -0.0001

Data Index: 1288130 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.2928. Min Act: -0.0001

Data Index: 413453 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3025. Min Act: -0.0001

Data Index: 651633 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.2877. Min Act: -0.0001

Data Index: 798715 (C4 (Web Text))

Max Activating Token Index: 232