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

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

Neuron 2325 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2658. Min Act: -0.0001

Data Index: 503763 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2362. Min Act: -0.0000

Data Index: 744283 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2450. Min Act: -0.0000

Data Index: 57651 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2294. Min Act: -0.0000

Data Index: 1238558 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2129. Min Act: -0.0000

Data Index: 467373 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2171. Min Act: -0.0000

Data Index: 552464 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2128. Min Act: -0.0001

Data Index: 541617 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2190. Min Act: -0.0000

Data Index: 1278816 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2007. Min Act: -0.0000

Data Index: 183656 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2114. Min Act: -0.0001

Data Index: 268202 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2049. Min Act: -0.0001

Data Index: 646253 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.2040. Min Act: -0.0000

Data Index: 900388 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.1961. Min Act: -0.0000

Data Index: 786037 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.1885. Min Act: -0.0000

Data Index: 329409 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.1882. Min Act: -0.0000

Data Index: 427009 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.1979. Min Act: -0.0001

Data Index: 393119 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.1840. Min Act: -0.0000

Data Index: 664400 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.1951. Min Act: -0.0001

Data Index: 998571 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.1819. Min Act: -0.0001

Data Index: 1567308 (Python Code)

Max Activating Token Index: 913

Text #19

Max Range: 0.2658. Min Range: -0.2658

Max Act: 0.1960. Min Act: -0.0000

Data Index: 414304 (C4 (Web Text))

Max Activating Token Index: 745