Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 881 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.7576. Min Act: -0.0001

Data Index: 1380647 (Python Code)

Max Activating Token Index: 68

Text #1

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.8099. Min Act: -0.0001

Data Index: 751096 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.7761. Min Act: -0.0001

Data Index: 1612618 (Python Code)

Max Activating Token Index: 1022

Text #3

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.7807. Min Act: -0.0001

Data Index: 981120 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.7390. Min Act: -0.0000

Data Index: 922837 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.7168. Min Act: -0.0001

Data Index: 1471512 (Python Code)

Max Activating Token Index: 699

Text #6

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.7254. Min Act: -0.0000

Data Index: 884114 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6927. Min Act: -0.0000

Data Index: 1094695 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.7256. Min Act: -0.0000

Data Index: 1168765 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6553. Min Act: -0.0000

Data Index: 560512 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6880. Min Act: -0.0000

Data Index: 386016 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6908. Min Act: -0.0001

Data Index: 147121 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6031. Min Act: -0.0001

Data Index: 1605121 (Python Code)

Max Activating Token Index: 934

Text #13

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6623. Min Act: -0.0000

Data Index: 1308235 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6405. Min Act: -0.0000

Data Index: 715305 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6415. Min Act: -0.0000

Data Index: 866720 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6583. Min Act: -0.0000

Data Index: 643939 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1223780 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6869. Min Act: -0.0000

Data Index: 116560 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6645. Min Act: -0.0000

Data Index: 622695 (C4 (Web Text))

Max Activating Token Index: 72