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

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

Neuron 3671 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2504. Min Range: -1.2504

Max Act: 1.2504. Min Act: -0.0000

Data Index: 1145336 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 1.2504. Min Range: -1.2504

Max Act: 1.0592. Min Act: -0.0000

Data Index: 1337685 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.9333. Min Act: -0.0001

Data Index: 1697 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.8994. Min Act: -0.0000

Data Index: 825340 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.9844. Min Act: -0.0000

Data Index: 977199 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.9797. Min Act: -0.0000

Data Index: 1071259 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.8956. Min Act: -0.0001

Data Index: 1380856 (Python Code)

Max Activating Token Index: 884

Text #7

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.9062. Min Act: -0.0001

Data Index: 1105192 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.8775. Min Act: -0.0000

Data Index: 1121768 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.7890. Min Act: -0.0000

Data Index: 316722 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.8458. Min Act: -0.0000

Data Index: 380816 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.8377. Min Act: -0.0000

Data Index: 714281 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.8357. Min Act: -0.0001

Data Index: 1036590 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.8163. Min Act: -0.0000

Data Index: 442634 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.8041. Min Act: -0.0000

Data Index: 36923 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.7779. Min Act: -0.0000

Data Index: 1256872 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.8500. Min Act: -0.0000

Data Index: 1295485 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.8022. Min Act: -0.0001

Data Index: 440727 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.7787. Min Act: -0.0001

Data Index: 501814 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.9020. Min Act: -0.0000

Data Index: 1241612 (C4 (Web Text))

Max Activating Token Index: 727