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

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

Neuron 3870 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: 0.3705. Min Range: -0.3705

Max Act: 0.3705. Min Act: -0.0000

Data Index: 1293553 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.3705. Min Range: -0.3705

Max Act: 0.3127. Min Act: -0.0001

Data Index: 654899 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.3705. Min Range: -0.3705

Max Act: 0.2762. Min Act: -0.0000

Data Index: 662736 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.3705. Min Range: -0.3705

Max Act: 0.2918. Min Act: -0.0000

Data Index: 1090560 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.3705. Min Range: -0.3705

Max Act: 0.2785. Min Act: -0.0001

Data Index: 653880 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 0.3705. Min Range: -0.3705

Max Act: 0.2884. Min Act: -0.0000

Data Index: 451048 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 0.3705. Min Range: -0.3705

Max Act: 0.2967. Min Act: -0.0001

Data Index: 1117369 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 0.3705. Min Range: -0.3705

Max Act: 0.2863. Min Act: -0.0000

Data Index: 349953 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.3705. Min Range: -0.3705

Max Act: 0.2705. Min Act: -0.0001

Data Index: 277647 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.3705. Min Range: -0.3705

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1333809 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.3705. Min Range: -0.3705

Max Act: 0.2659. Min Act: -0.0000

Data Index: 772353 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.3705. Min Range: -0.3705

Max Act: 0.2594. Min Act: -0.0000

Data Index: 362449 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 0.3705. Min Range: -0.3705

Max Act: 0.2472. Min Act: -0.0000

Data Index: 943746 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 0.3705. Min Range: -0.3705

Max Act: 0.2563. Min Act: -0.0000

Data Index: 1107976 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 0.3705. Min Range: -0.3705

Max Act: 0.2601. Min Act: -0.0001

Data Index: 461632 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 0.3705. Min Range: -0.3705

Max Act: 0.2589. Min Act: -0.0001

Data Index: 172850 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.3705. Min Range: -0.3705

Max Act: 0.2554. Min Act: -0.0001

Data Index: 1149853 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.3705. Min Range: -0.3705

Max Act: 0.2462. Min Act: -0.0000

Data Index: 643378 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.3705. Min Range: -0.3705

Max Act: 0.2457. Min Act: -0.0000

Data Index: 809480 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.3705. Min Range: -0.3705

Max Act: 0.2380. Min Act: -0.0000

Data Index: 1324813 (C4 (Web Text))

Max Activating Token Index: 41