Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2979 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.8265. Min Act: -0.0001

Data Index: 1211326 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.4323. Min Act: -0.0001

Data Index: 167227 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.4700. Min Act: -0.0001

Data Index: 204150 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.2657. Min Act: -0.0001

Data Index: 1218778 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.1673. Min Act: -0.0001

Data Index: 143507 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.2261. Min Act: -0.0001

Data Index: 671242 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.3043. Min Act: -0.0001

Data Index: 599005 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.1900. Min Act: -0.0001

Data Index: 864741 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.1367. Min Act: -0.0001

Data Index: 1142410 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.0861. Min Act: -0.0001

Data Index: 1235647 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.1464. Min Act: -0.0001

Data Index: 705094 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.1231. Min Act: -0.0001

Data Index: 381320 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.1053. Min Act: -0.0001

Data Index: 283851 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.0986. Min Act: -0.0001

Data Index: 404446 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.0388. Min Act: -0.0001

Data Index: 1353696 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.0657. Min Act: -0.0001

Data Index: 1280224 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.0212. Min Act: -0.0001

Data Index: 606642 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.1521. Min Act: -0.0001

Data Index: 259422 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.0760. Min Act: -0.0001

Data Index: 564634 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.0352. Min Act: -0.0001

Data Index: 423127 (C4 (Web Text))

Max Activating Token Index: 55