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

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

Neuron 1304 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1016073 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.6105. Min Act: -0.0000

Data Index: 333350 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.6414. Min Act: -0.0000

Data Index: 257854 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5899. Min Act: -0.0000

Data Index: 917053 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5437. Min Act: -0.0000

Data Index: 363360 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1311456 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5666. Min Act: -0.0001

Data Index: 898085 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5182. Min Act: -0.0000

Data Index: 534460 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5602. Min Act: -0.0000

Data Index: 631490 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5384. Min Act: -0.0000

Data Index: 695567 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5066. Min Act: -0.0000

Data Index: 105669 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5523. Min Act: -0.0000

Data Index: 1071387 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5510. Min Act: -0.0000

Data Index: 447003 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5000. Min Act: -0.0000

Data Index: 1148391 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5321. Min Act: -0.0001

Data Index: 1276892 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.4865. Min Act: -0.0000

Data Index: 67643 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5173. Min Act: -0.0001

Data Index: 1011242 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.4965. Min Act: -0.0000

Data Index: 998899 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.4335. Min Act: -0.0000

Data Index: 348464 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.4547. Min Act: -0.0001

Data Index: 162248 (C4 (Web Text))

Max Activating Token Index: 793