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

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

Neuron 4818 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: 0.4597. Min Range: -0.4597

Max Act: 0.4597. Min Act: -0.0000

Data Index: 851660 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.4056. Min Act: -0.0000

Data Index: 113010 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1052824 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3039. Min Act: -0.0000

Data Index: 671716 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2798. Min Act: -0.0000

Data Index: 810463 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1324733 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2901. Min Act: -0.0000

Data Index: 901400 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2923. Min Act: -0.0000

Data Index: 1190507 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2916. Min Act: -0.0000

Data Index: 534237 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2555. Min Act: -0.0000

Data Index: 1022070 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2534. Min Act: -0.0000

Data Index: 784658 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2693. Min Act: -0.0000

Data Index: 820778 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2680. Min Act: -0.0000

Data Index: 419478 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2488. Min Act: -0.0000

Data Index: 1121286 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2456. Min Act: -0.0000

Data Index: 863499 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2506. Min Act: -0.0000

Data Index: 100721 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2380. Min Act: -0.0000

Data Index: 779603 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2480. Min Act: -0.0000

Data Index: 668006 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2477. Min Act: -0.0000

Data Index: 23183 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2460. Min Act: -0.0000

Data Index: 1249897 (C4 (Web Text))

Max Activating Token Index: 1009