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

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

Neuron 1185 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5554. Min Range: -1.5554

Max Act: 1.5554. Min Act: -0.0001

Data Index: 480474 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 1.5554. Min Range: -1.5554

Max Act: 1.4689. Min Act: -0.0001

Data Index: 644683 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 1.5554. Min Range: -1.5554

Max Act: 1.4123. Min Act: -0.0001

Data Index: 742566 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 1.5554. Min Range: -1.5554

Max Act: 1.4843. Min Act: -0.0001

Data Index: 325131 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 1.5554. Min Range: -1.5554

Max Act: 1.4535. Min Act: -0.0000

Data Index: 71268 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 1.5554. Min Range: -1.5554

Max Act: 1.2758. Min Act: -0.0001

Data Index: 176396 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 1.5554. Min Range: -1.5554

Max Act: 1.2864. Min Act: -0.0001

Data Index: 328149 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 1.5554. Min Range: -1.5554

Max Act: 1.1654. Min Act: -0.0001

Data Index: 169783 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 1.5554. Min Range: -1.5554

Max Act: 1.3508. Min Act: -0.0001

Data Index: 3377 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 1.5554. Min Range: -1.5554

Max Act: 1.0928. Min Act: -0.0001

Data Index: 982983 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 1.5554. Min Range: -1.5554

Max Act: 1.2145. Min Act: -0.0001

Data Index: 447782 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 1.5554. Min Range: -1.5554

Max Act: 1.2153. Min Act: -0.0001

Data Index: 205503 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 1.5554. Min Range: -1.5554

Max Act: 1.1012. Min Act: -0.0001

Data Index: 488539 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 1.5554. Min Range: -1.5554

Max Act: 1.2560. Min Act: -0.0001

Data Index: 114586 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 1.5554. Min Range: -1.5554

Max Act: 1.1893. Min Act: -0.0001

Data Index: 473710 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 1.5554. Min Range: -1.5554

Max Act: 1.0749. Min Act: -0.0001

Data Index: 505288 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 1.5554. Min Range: -1.5554

Max Act: 1.2093. Min Act: -0.0001

Data Index: 350266 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 1.5554. Min Range: -1.5554

Max Act: 1.1908. Min Act: -0.0001

Data Index: 290457 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 1.5554. Min Range: -1.5554

Max Act: 1.2433. Min Act: -0.0001

Data Index: 1025365 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 1.5554. Min Range: -1.5554

Max Act: 1.1262. Min Act: -0.0001

Data Index: 1315287 (C4 (Web Text))

Max Activating Token Index: 695