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

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

Neuron 4503 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2936. Min Range: -3.2936

Max Act: 3.2936. Min Act: -0.0000

Data Index: 1209402 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 3.2936. Min Range: -3.2936

Max Act: 2.8144. Min Act: -0.0000

Data Index: 1286275 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 3.2936. Min Range: -3.2936

Max Act: 2.7897. Min Act: -0.0000

Data Index: 160543 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 3.2936. Min Range: -3.2936

Max Act: 2.7800. Min Act: -0.0000

Data Index: 903619 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 3.2936. Min Range: -3.2936

Max Act: 2.3005. Min Act: -0.0000

Data Index: 1178542 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 3.2936. Min Range: -3.2936

Max Act: 2.4179. Min Act: -0.0000

Data Index: 1211089 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 3.2936. Min Range: -3.2936

Max Act: 2.2170. Min Act: -0.0000

Data Index: 1248858 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 3.2936. Min Range: -3.2936

Max Act: 2.3220. Min Act: -0.0000

Data Index: 37631 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 3.2936. Min Range: -3.2936

Max Act: 2.2776. Min Act: -0.0000

Data Index: 28678 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 3.2936. Min Range: -3.2936

Max Act: 2.2579. Min Act: -0.0000

Data Index: 431552 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 3.2936. Min Range: -3.2936

Max Act: 2.3540. Min Act: -0.0000

Data Index: 220204 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 3.2936. Min Range: -3.2936

Max Act: 2.2565. Min Act: -0.0000

Data Index: 69672 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 3.2936. Min Range: -3.2936

Max Act: 2.2054. Min Act: -0.0000

Data Index: 493362 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 3.2936. Min Range: -3.2936

Max Act: 2.2088. Min Act: -0.0000

Data Index: 1080052 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 3.2936. Min Range: -3.2936

Max Act: 2.1177. Min Act: -0.0000

Data Index: 670879 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 3.2936. Min Range: -3.2936

Max Act: 2.1557. Min Act: -0.0000

Data Index: 372688 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 3.2936. Min Range: -3.2936

Max Act: 2.0964. Min Act: -0.0000

Data Index: 589278 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 3.2936. Min Range: -3.2936

Max Act: 2.2456. Min Act: -0.0000

Data Index: 268303 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 3.2936. Min Range: -3.2936

Max Act: 2.0832. Min Act: -0.0000

Data Index: 563538 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 3.2936. Min Range: -3.2936

Max Act: 2.0844. Min Act: -0.0000

Data Index: 1151793 (C4 (Web Text))

Max Activating Token Index: 619