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

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

Neuron 433 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.7548. Min Act: -0.0000

Data Index: 554793 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.7191. Min Act: -0.0000

Data Index: 884636 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.7217. Min Act: -0.0000

Data Index: 428105 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6428. Min Act: -0.0000

Data Index: 117192 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6593. Min Act: 0.0000

Data Index: 539505 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6235. Min Act: -0.0000

Data Index: 617144 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6068. Min Act: -0.0000

Data Index: 987836 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6268. Min Act: -0.0000

Data Index: 3905 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6268. Min Act: -0.0000

Data Index: 499622 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5802. Min Act: -0.0000

Data Index: 684310 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6145. Min Act: -0.0000

Data Index: 805087 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6384. Min Act: -0.0000

Data Index: 509772 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5682. Min Act: 0.0001

Data Index: 1264685 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5650. Min Act: -0.0000

Data Index: 97128 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5489. Min Act: -0.0000

Data Index: 556347 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5759. Min Act: -0.0000

Data Index: 1209829 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5798. Min Act: -0.0000

Data Index: 1218185 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5585. Min Act: 0.0000

Data Index: 1026728 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5762. Min Act: -0.0000

Data Index: 57392 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5560. Min Act: -0.0000

Data Index: 206113 (C4 (Web Text))

Max Activating Token Index: 274