Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4111 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1055163 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.6086. Min Act: -0.0000

Data Index: 498085 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.7006. Min Act: -0.0000

Data Index: 107955 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.5792. Min Act: -0.0000

Data Index: 302154 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.5635. Min Act: -0.0000

Data Index: 862940 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.4634. Min Act: -0.0000

Data Index: 329542 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1233220 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.4856. Min Act: -0.0000

Data Index: 536032 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.4624. Min Act: -0.0000

Data Index: 1240432 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.4675. Min Act: -0.0000

Data Index: 769871 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.4625. Min Act: -0.0000

Data Index: 23767 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.4172. Min Act: -0.0000

Data Index: 543746 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.4325. Min Act: -0.0000

Data Index: 848177 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.4245. Min Act: -0.0000

Data Index: 758955 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.3601. Min Act: -0.0000

Data Index: 124169 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.4408. Min Act: -0.0000

Data Index: 435078 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.4330. Min Act: -0.0000

Data Index: 568982 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.4085. Min Act: -0.0000

Data Index: 1235324 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.4142. Min Act: -0.0000

Data Index: 926749 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.4474. Min Act: -0.0000

Data Index: 162904 (C4 (Web Text))

Max Activating Token Index: 249