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

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

Neuron 802 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.6997. Min Act: -0.0001

Data Index: 1493973 (Python Code)

Max Activating Token Index: 418

Text #1

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.7642. Min Act: -0.0001

Data Index: 1629237 (Python Code)

Max Activating Token Index: 558

Text #2

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.7069. Min Act: -0.0001

Data Index: 1541995 (Python Code)

Max Activating Token Index: 619

Text #3

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.7488. Min Act: -0.0001

Data Index: 1425312 (Python Code)

Max Activating Token Index: 193

Text #4

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.6563. Min Act: -0.0001

Data Index: 1431793 (Python Code)

Max Activating Token Index: 994

Text #5

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.6610. Min Act: -0.0001

Data Index: 1592658 (Python Code)

Max Activating Token Index: 206

Text #6

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.4795. Min Act: -0.0001

Data Index: 1011354 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.4893. Min Act: -0.0002

Data Index: 482244 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.3972. Min Act: -0.0002

Data Index: 802890 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.3985. Min Act: -0.0001

Data Index: 860359 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.4480. Min Act: -0.0001

Data Index: 1290260 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.5247. Min Act: -0.0001

Data Index: 297807 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.4555. Min Act: -0.0001

Data Index: 357421 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.4672. Min Act: -0.0001

Data Index: 183754 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.4933. Min Act: -0.0002

Data Index: 853905 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.5279. Min Act: -0.0002

Data Index: 361500 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.3960. Min Act: -0.0001

Data Index: 1190380 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.4346. Min Act: -0.0002

Data Index: 305355 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.4333. Min Act: -0.0002

Data Index: 1189486 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.4078. Min Act: -0.0002

Data Index: 337358 (C4 (Web Text))

Max Activating Token Index: 870