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

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

Neuron 3637 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9584. Min Range: -1.9584

Max Act: 1.9584. Min Act: -0.0001

Data Index: 118618 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 1.9584. Min Range: -1.9584

Max Act: 1.7014. Min Act: -0.0001

Data Index: 1299476 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 1.9584. Min Range: -1.9584

Max Act: 1.6249. Min Act: -0.0001

Data Index: 280271 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 1.9584. Min Range: -1.9584

Max Act: 1.5080. Min Act: -0.0001

Data Index: 1115405 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 1.9584. Min Range: -1.9584

Max Act: 1.6087. Min Act: -0.0001

Data Index: 726559 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 1.9584. Min Range: -1.9584

Max Act: 1.6255. Min Act: -0.0001

Data Index: 864812 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 1.9584. Min Range: -1.9584

Max Act: 1.5498. Min Act: -0.0001

Data Index: 347341 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 1.9584. Min Range: -1.9584

Max Act: 1.4665. Min Act: -0.0001

Data Index: 627696 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 1.9584. Min Range: -1.9584

Max Act: 1.6718. Min Act: -0.0001

Data Index: 54192 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 1.9584. Min Range: -1.9584

Max Act: 1.4110. Min Act: -0.0001

Data Index: 1255381 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 1.9584. Min Range: -1.9584

Max Act: 1.4796. Min Act: -0.0001

Data Index: 164881 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 1.9584. Min Range: -1.9584

Max Act: 1.4565. Min Act: -0.0001

Data Index: 1085604 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 1.9584. Min Range: -1.9584

Max Act: 1.4517. Min Act: -0.0001

Data Index: 488371 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 1.9584. Min Range: -1.9584

Max Act: 1.4511. Min Act: -0.0001

Data Index: 779587 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 1.9584. Min Range: -1.9584

Max Act: 1.5266. Min Act: -0.0001

Data Index: 420534 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 1.9584. Min Range: -1.9584

Max Act: 1.4768. Min Act: -0.0001

Data Index: 942260 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 1.9584. Min Range: -1.9584

Max Act: 1.5092. Min Act: -0.0001

Data Index: 289084 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 1.9584. Min Range: -1.9584

Max Act: 1.4113. Min Act: -0.0001

Data Index: 40567 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 1.9584. Min Range: -1.9584

Max Act: 1.2405. Min Act: -0.0001

Data Index: 79307 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 1.9584. Min Range: -1.9584

Max Act: 1.4078. Min Act: -0.0001

Data Index: 1242511 (C4 (Web Text))

Max Activating Token Index: 239