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

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

Neuron 4622 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5552. Min Range: -1.5552

Max Act: 1.5552. Min Act: -0.0000

Data Index: 369870 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 1.5552. Min Range: -1.5552

Max Act: 1.3295. Min Act: -0.0000

Data Index: 928023 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 1.5552. Min Range: -1.5552

Max Act: 1.2971. Min Act: -0.0000

Data Index: 985195 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 1.5552. Min Range: -1.5552

Max Act: 1.1155. Min Act: -0.0000

Data Index: 102997 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 1.5552. Min Range: -1.5552

Max Act: 1.0722. Min Act: -0.0000

Data Index: 474831 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 1.5552. Min Range: -1.5552

Max Act: 0.9492. Min Act: -0.0000

Data Index: 386506 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 1.5552. Min Range: -1.5552

Max Act: 0.9881. Min Act: -0.0000

Data Index: 1341399 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 1.5552. Min Range: -1.5552

Max Act: 0.9579. Min Act: -0.0000

Data Index: 746849 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 1.5552. Min Range: -1.5552

Max Act: 0.8866. Min Act: -0.0000

Data Index: 690835 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 1.5552. Min Range: -1.5552

Max Act: 0.9511. Min Act: -0.0000

Data Index: 200817 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 1.5552. Min Range: -1.5552

Max Act: 0.9065. Min Act: -0.0000

Data Index: 942186 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 1.5552. Min Range: -1.5552

Max Act: 0.9053. Min Act: -0.0000

Data Index: 1327947 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 1.5552. Min Range: -1.5552

Max Act: 0.9439. Min Act: -0.0000

Data Index: 876308 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 1.5552. Min Range: -1.5552

Max Act: 0.9135. Min Act: -0.0000

Data Index: 1592207 (Python Code)

Max Activating Token Index: 407

Text #14

Max Range: 1.5552. Min Range: -1.5552

Max Act: 0.8979. Min Act: -0.0000

Data Index: 147328 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 1.5552. Min Range: -1.5552

Max Act: 0.9349. Min Act: -0.0000

Data Index: 220229 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 1.5552. Min Range: -1.5552

Max Act: 0.8543. Min Act: -0.0000

Data Index: 87567 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 1.5552. Min Range: -1.5552

Max Act: 0.9025. Min Act: -0.0000

Data Index: 401792 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 1.5552. Min Range: -1.5552

Max Act: 0.8742. Min Act: -0.0000

Data Index: 540979 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 1.5552. Min Range: -1.5552

Max Act: 0.9036. Min Act: -0.0000

Data Index: 167599 (C4 (Web Text))

Max Activating Token Index: 416