Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4396 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0536. Min Range: -1.0536

Max Act: 1.0425. Min Act: -0.0001

Data Index: 756714 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 1.0536. Min Range: -1.0536

Max Act: 1.0536. Min Act: -0.0001

Data Index: 480573 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 1.0536. Min Range: -1.0536

Max Act: 1.0171. Min Act: -0.0001

Data Index: 1157748 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.9799. Min Act: -0.0001

Data Index: 864879 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.9687. Min Act: -0.0001

Data Index: 751111 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.9411. Min Act: -0.0001

Data Index: 252666 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.9253. Min Act: -0.0001

Data Index: 1346267 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8312. Min Act: -0.0001

Data Index: 1188806 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8608. Min Act: -0.0001

Data Index: 639442 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8976. Min Act: -0.0001

Data Index: 672151 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8551. Min Act: -0.0001

Data Index: 51320 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8074. Min Act: -0.0001

Data Index: 449237 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.9053. Min Act: -0.0001

Data Index: 145293 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8725. Min Act: -0.0001

Data Index: 361417 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8376. Min Act: -0.0001

Data Index: 1294554 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8538. Min Act: -0.0001

Data Index: 1344982 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8065. Min Act: -0.0001

Data Index: 503050 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8521. Min Act: -0.0001

Data Index: 337831 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8748. Min Act: -0.0001

Data Index: 152185 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.7651. Min Act: -0.0001

Data Index: 744265 (C4 (Web Text))

Max Activating Token Index: 89