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

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

Neuron 4354 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.8315. Min Act: -0.0000

Data Index: 585207 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.7694. Min Act: -0.0000

Data Index: 986884 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.6526. Min Act: -0.0000

Data Index: 347899 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.6360. Min Act: -0.0000

Data Index: 432138 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.6068. Min Act: -0.0000

Data Index: 1374058 (Python Code)

Max Activating Token Index: 904

Text #5

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.5160. Min Act: -0.0000

Data Index: 299832 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.4772. Min Act: -0.0000

Data Index: 512918 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.4303. Min Act: -0.0000

Data Index: 1448774 (Python Code)

Max Activating Token Index: 268

Text #8

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.5250. Min Act: -0.0000

Data Index: 984092 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1469073 (Python Code)

Max Activating Token Index: 511

Text #10

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.5003. Min Act: -0.0000

Data Index: 1500069 (Python Code)

Max Activating Token Index: 14

Text #11

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1558283 (Python Code)

Max Activating Token Index: 89

Text #12

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.4645. Min Act: -0.0000

Data Index: 571208 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.4633. Min Act: -0.0000

Data Index: 410946 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1450827 (Python Code)

Max Activating Token Index: 542

Text #15

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.4499. Min Act: -0.0000

Data Index: 1482954 (Python Code)

Max Activating Token Index: 227

Text #16

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.4566. Min Act: -0.0000

Data Index: 1534836 (Python Code)

Max Activating Token Index: 88

Text #17

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.3969. Min Act: -0.0000

Data Index: 1121493 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.4752. Min Act: -0.0000

Data Index: 580296 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.8315. Min Range: -0.8315

Max Act: 0.4215. Min Act: -0.0000

Data Index: 182032 (C4 (Web Text))

Max Activating Token Index: 884