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

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

Neuron 5183 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.4685. Min Act: -0.0000

Data Index: 154266 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.3118. Min Act: -0.0000

Data Index: 1278465 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.2341. Min Act: -0.0000

Data Index: 688508 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.2542. Min Act: -0.0000

Data Index: 573912 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.1866. Min Act: -0.0000

Data Index: 981126 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.1874. Min Act: 0.0001

Data Index: 71936 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.0846. Min Act: -0.0000

Data Index: 868688 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.0037. Min Act: -0.0000

Data Index: 681874 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.0337. Min Act: -0.0000

Data Index: 13368 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.0177. Min Act: -0.0000

Data Index: 261544 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.0025. Min Act: -0.0000

Data Index: 1215598 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.0012. Min Act: -0.0000

Data Index: 487492 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.0534. Min Act: -0.0000

Data Index: 403215 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.9928. Min Act: -0.0000

Data Index: 1171998 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.9463. Min Act: -0.0000

Data Index: 110726 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.9439. Min Act: 0.0000

Data Index: 386382 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.9374. Min Act: -0.0000

Data Index: 302892 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.9377. Min Act: -0.0000

Data Index: 82323 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.9091. Min Act: 0.0000

Data Index: 460718 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.8961. Min Act: 0.0000

Data Index: 1218952 (C4 (Web Text))

Max Activating Token Index: 755