Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4614 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.3137. Min Act: -0.0000

Data Index: 25070 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.3450. Min Act: -0.0000

Data Index: 869462 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2772. Min Act: -0.0000

Data Index: 364538 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2692. Min Act: -0.0000

Data Index: 409631 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2964. Min Act: -0.0000

Data Index: 512753 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2974. Min Act: -0.0000

Data Index: 1265521 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1021231 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2881. Min Act: -0.0000

Data Index: 60871 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2724. Min Act: -0.0000

Data Index: 72967 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2806. Min Act: -0.0000

Data Index: 1032071 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2576. Min Act: -0.0000

Data Index: 1010836 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2525. Min Act: -0.0000

Data Index: 200453 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2509. Min Act: -0.0000

Data Index: 456891 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2830. Min Act: -0.0000

Data Index: 1066141 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2463. Min Act: -0.0000

Data Index: 426431 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2719. Min Act: -0.0000

Data Index: 1221248 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2469. Min Act: -0.0000

Data Index: 1493764 (Python Code)

Max Activating Token Index: 438

Text #17

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2465. Min Act: -0.0000

Data Index: 979681 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2468. Min Act: -0.0000

Data Index: 964499 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2452. Min Act: -0.0000

Data Index: 57935 (C4 (Web Text))

Max Activating Token Index: 1018