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

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

Neuron 3384 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.9822. Min Act: -0.0001

Data Index: 1137037 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.9889. Min Act: -0.0001

Data Index: 431923 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 1.0055. Min Range: -1.0055

Max Act: 1.0055. Min Act: -0.0001

Data Index: 1197117 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.9721. Min Act: -0.0001

Data Index: 1344820 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.9324. Min Act: -0.0002

Data Index: 1331082 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8957. Min Act: -0.0001

Data Index: 1265718 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.9113. Min Act: -0.0001

Data Index: 842303 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8905. Min Act: -0.0002

Data Index: 491699 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8451. Min Act: -0.0001

Data Index: 857509 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8926. Min Act: -0.0001

Data Index: 661770 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8928. Min Act: -0.0001

Data Index: 478351 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8260. Min Act: -0.0001

Data Index: 1051791 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.9269. Min Act: -0.0001

Data Index: 983559 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8294. Min Act: -0.0001

Data Index: 934212 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8399. Min Act: -0.0001

Data Index: 895928 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8550. Min Act: -0.0002

Data Index: 394649 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8503. Min Act: -0.0001

Data Index: 893138 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8949. Min Act: -0.0001

Data Index: 1184866 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8937. Min Act: -0.0001

Data Index: 1043012 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8449. Min Act: -0.0001

Data Index: 889379 (C4 (Web Text))

Max Activating Token Index: 1002