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

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

Neuron 2411 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4379. Min Range: -0.4379

Max Act: 0.4379. Min Act: -0.0000

Data Index: 922618 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 0.4379. Min Range: -0.4379

Max Act: 0.3748. Min Act: -0.0000

Data Index: 50657 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.4379. Min Range: -0.4379

Max Act: 0.2994. Min Act: -0.0000

Data Index: 365293 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.4379. Min Range: -0.4379

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1217171 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 0.4379. Min Range: -0.4379

Max Act: 0.3048. Min Act: -0.0000

Data Index: 38056 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 0.4379. Min Range: -0.4379

Max Act: 0.2943. Min Act: -0.0000

Data Index: 920083 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 0.4379. Min Range: -0.4379

Max Act: 0.2883. Min Act: -0.0000

Data Index: 648041 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 0.4379. Min Range: -0.4379

Max Act: 0.2450. Min Act: -0.0000

Data Index: 447950 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 0.4379. Min Range: -0.4379

Max Act: 0.2807. Min Act: -0.0000

Data Index: 545751 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.4379. Min Range: -0.4379

Max Act: 0.2472. Min Act: -0.0000

Data Index: 504028 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 0.4379. Min Range: -0.4379

Max Act: 0.2849. Min Act: -0.0000

Data Index: 820274 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.4379. Min Range: -0.4379

Max Act: 0.2461. Min Act: -0.0000

Data Index: 751689 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.4379. Min Range: -0.4379

Max Act: 0.2880. Min Act: -0.0000

Data Index: 491599 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 0.4379. Min Range: -0.4379

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1302109 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.4379. Min Range: -0.4379

Max Act: 0.2378. Min Act: -0.0000

Data Index: 56374 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.4379. Min Range: -0.4379

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1116108 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.4379. Min Range: -0.4379

Max Act: 0.2724. Min Act: -0.0000

Data Index: 395025 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.4379. Min Range: -0.4379

Max Act: 0.2589. Min Act: -0.0000

Data Index: 769603 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.4379. Min Range: -0.4379

Max Act: 0.2483. Min Act: -0.0000

Data Index: 962610 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.4379. Min Range: -0.4379

Max Act: 0.2312. Min Act: -0.0000

Data Index: 942696 (C4 (Web Text))

Max Activating Token Index: 428