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

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

Neuron 3971 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: 3.3755. Min Range: -3.3755

Max Act: 3.3755. Min Act: -0.0001

Data Index: 300614 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.1546. Min Act: -0.0001

Data Index: 1234476 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 3.3755. Min Range: -3.3755

Max Act: 2.9879. Min Act: -0.0001

Data Index: 578762 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.1197. Min Act: -0.0001

Data Index: 1159729 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 3.3755. Min Range: -3.3755

Max Act: 3.0082. Min Act: -0.0001

Data Index: 40499 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 3.3755. Min Range: -3.3755

Max Act: 2.7342. Min Act: -0.0001

Data Index: 1189785 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 3.3755. Min Range: -3.3755

Max Act: 2.5705. Min Act: -0.0001

Data Index: 42034 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 3.3755. Min Range: -3.3755

Max Act: 2.4397. Min Act: -0.0001

Data Index: 648112 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 3.3755. Min Range: -3.3755

Max Act: 2.5290. Min Act: -0.0001

Data Index: 406241 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 3.3755. Min Range: -3.3755

Max Act: 2.4546. Min Act: -0.0001

Data Index: 928957 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 3.3755. Min Range: -3.3755

Max Act: 2.3593. Min Act: -0.0001

Data Index: 1071018 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 3.3755. Min Range: -3.3755

Max Act: 2.7225. Min Act: -0.0001

Data Index: 883983 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 3.3755. Min Range: -3.3755

Max Act: 2.4070. Min Act: -0.0001

Data Index: 1284454 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 3.3755. Min Range: -3.3755

Max Act: 2.4862. Min Act: -0.0000

Data Index: 681114 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 3.3755. Min Range: -3.3755

Max Act: 2.2954. Min Act: -0.0000

Data Index: 806521 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 3.3755. Min Range: -3.3755

Max Act: 2.3022. Min Act: -0.0001

Data Index: 735328 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 3.3755. Min Range: -3.3755

Max Act: 2.2597. Min Act: -0.0000

Data Index: 701024 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 3.3755. Min Range: -3.3755

Max Act: 2.2058. Min Act: -0.0001

Data Index: 767344 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 3.3755. Min Range: -3.3755

Max Act: 2.1735. Min Act: -0.0001

Data Index: 363004 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 3.3755. Min Range: -3.3755

Max Act: 2.2250. Min Act: -0.0001

Data Index: 170430 (C4 (Web Text))

Max Activating Token Index: 540