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

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

Neuron 1082 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8990. Min Range: -2.8990

Max Act: 2.8990. Min Act: -0.0000

Data Index: 355617 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 2.8990. Min Range: -2.8990

Max Act: 2.5363. Min Act: -0.0000

Data Index: 968121 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 2.8990. Min Range: -2.8990

Max Act: 1.8777. Min Act: -0.0000

Data Index: 975400 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 2.8990. Min Range: -2.8990

Max Act: 1.8059. Min Act: -0.0001

Data Index: 1242124 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 2.8990. Min Range: -2.8990

Max Act: 1.7585. Min Act: -0.0000

Data Index: 1274735 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 2.8990. Min Range: -2.8990

Max Act: 1.8490. Min Act: -0.0000

Data Index: 84821 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 2.8990. Min Range: -2.8990

Max Act: 1.8336. Min Act: -0.0000

Data Index: 382450 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 2.8990. Min Range: -2.8990

Max Act: 1.9408. Min Act: -0.0000

Data Index: 496973 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 2.8990. Min Range: -2.8990

Max Act: 1.5967. Min Act: -0.0000

Data Index: 321233 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 2.8990. Min Range: -2.8990

Max Act: 1.8824. Min Act: -0.0000

Data Index: 150676 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 2.8990. Min Range: -2.8990

Max Act: 1.7161. Min Act: -0.0000

Data Index: 163021 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 2.8990. Min Range: -2.8990

Max Act: 1.7022. Min Act: -0.0000

Data Index: 65972 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 2.8990. Min Range: -2.8990

Max Act: 1.6683. Min Act: -0.0000

Data Index: 69397 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 2.8990. Min Range: -2.8990

Max Act: 1.5629. Min Act: -0.0000

Data Index: 1356885 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 2.8990. Min Range: -2.8990

Max Act: 1.6659. Min Act: -0.0000

Data Index: 446279 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 2.8990. Min Range: -2.8990

Max Act: 1.6620. Min Act: -0.0000

Data Index: 27539 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 2.8990. Min Range: -2.8990

Max Act: 1.6399. Min Act: -0.0000

Data Index: 789117 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 2.8990. Min Range: -2.8990

Max Act: 1.7347. Min Act: -0.0000

Data Index: 658821 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 2.8990. Min Range: -2.8990

Max Act: 1.6415. Min Act: -0.0000

Data Index: 1323955 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 2.8990. Min Range: -2.8990

Max Act: 1.5115. Min Act: -0.0000

Data Index: 588291 (C4 (Web Text))

Max Activating Token Index: 463