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

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

Neuron 3938 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4170. Min Range: -1.4170

Max Act: 1.4170. Min Act: -0.0000

Data Index: 192220 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 1.4170. Min Range: -1.4170

Max Act: 1.3762. Min Act: -0.0000

Data Index: 1172051 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 1.4170. Min Range: -1.4170

Max Act: 1.0022. Min Act: -0.0000

Data Index: 548096 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 1.4170. Min Range: -1.4170

Max Act: 1.0840. Min Act: -0.0000

Data Index: 92633 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 1.4170. Min Range: -1.4170

Max Act: 1.1491. Min Act: -0.0000

Data Index: 169959 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.9411. Min Act: -0.0000

Data Index: 96492 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 1.4170. Min Range: -1.4170

Max Act: 1.0615. Min Act: -0.0000

Data Index: 879808 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 1.4170. Min Range: -1.4170

Max Act: 1.0304. Min Act: -0.0000

Data Index: 869083 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.8912. Min Act: -0.0000

Data Index: 573492 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.9972. Min Act: -0.0000

Data Index: 231341 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.9221. Min Act: -0.0000

Data Index: 309594 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.9065. Min Act: -0.0000

Data Index: 453851 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.8959. Min Act: -0.0000

Data Index: 23079 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.8894. Min Act: -0.0000

Data Index: 862014 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.8289. Min Act: -0.0000

Data Index: 683534 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.8871. Min Act: -0.0000

Data Index: 403441 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.8062. Min Act: -0.0000

Data Index: 536158 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.8452. Min Act: -0.0000

Data Index: 599977 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.8268. Min Act: -0.0000

Data Index: 909361 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 1.4170. Min Range: -1.4170

Max Act: 0.9029. Min Act: -0.0000

Data Index: 868885 (C4 (Web Text))

Max Activating Token Index: 293