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

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

Neuron 1444 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7448. Min Range: -1.7448

Max Act: 1.7424. Min Act: -0.0001

Data Index: 1045869 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 1.7448. Min Range: -1.7448

Max Act: 1.7448. Min Act: -0.0001

Data Index: 203553 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 1.7448. Min Range: -1.7448

Max Act: 1.6594. Min Act: -0.0000

Data Index: 1268639 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 1.7448. Min Range: -1.7448

Max Act: 1.6413. Min Act: -0.0001

Data Index: 551003 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 1.7448. Min Range: -1.7448

Max Act: 1.4853. Min Act: -0.0000

Data Index: 1059665 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 1.7448. Min Range: -1.7448

Max Act: 1.5637. Min Act: -0.0001

Data Index: 72926 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 1.7448. Min Range: -1.7448

Max Act: 1.4877. Min Act: -0.0001

Data Index: 552896 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 1.7448. Min Range: -1.7448

Max Act: 1.4547. Min Act: -0.0001

Data Index: 267436 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 1.7448. Min Range: -1.7448

Max Act: 1.4508. Min Act: -0.0000

Data Index: 1155822 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 1.7448. Min Range: -1.7448

Max Act: 1.6215. Min Act: -0.0001

Data Index: 221181 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 1.7448. Min Range: -1.7448

Max Act: 1.6136. Min Act: -0.0000

Data Index: 558651 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 1.7448. Min Range: -1.7448

Max Act: 1.4883. Min Act: -0.0001

Data Index: 770242 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 1.7448. Min Range: -1.7448

Max Act: 1.5205. Min Act: -0.0001

Data Index: 1338058 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 1.7448. Min Range: -1.7448

Max Act: 1.5155. Min Act: -0.0000

Data Index: 450415 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 1.7448. Min Range: -1.7448

Max Act: 1.5194. Min Act: -0.0000

Data Index: 1157953 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 1.7448. Min Range: -1.7448

Max Act: 1.5162. Min Act: -0.0000

Data Index: 1132904 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 1.7448. Min Range: -1.7448

Max Act: 1.4997. Min Act: -0.0000

Data Index: 558620 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 1.7448. Min Range: -1.7448

Max Act: 1.5052. Min Act: -0.0000

Data Index: 1327392 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 1.7448. Min Range: -1.7448

Max Act: 1.5700. Min Act: -0.0000

Data Index: 977774 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 1.7448. Min Range: -1.7448

Max Act: 1.3827. Min Act: -0.0000

Data Index: 734659 (C4 (Web Text))

Max Activating Token Index: 478