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

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

Neuron 3108 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: 0.8527. Min Range: -0.8527

Max Act: 0.8154. Min Act: -0.0001

Data Index: 505616 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.8527. Min Act: -0.0001

Data Index: 1344112 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6698. Min Act: -0.0001

Data Index: 790560 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7172. Min Act: -0.0001

Data Index: 937135 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7097. Min Act: -0.0001

Data Index: 51478 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6096. Min Act: -0.0001

Data Index: 1291751 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6794. Min Act: -0.0001

Data Index: 56580 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5898. Min Act: -0.0001

Data Index: 534674 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5700. Min Act: -0.0002

Data Index: 68500 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5816. Min Act: -0.0001

Data Index: 644151 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6680. Min Act: -0.0001

Data Index: 968001 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5583. Min Act: -0.0001

Data Index: 759482 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5392. Min Act: -0.0001

Data Index: 382245 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6466. Min Act: -0.0002

Data Index: 412786 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5653. Min Act: -0.0002

Data Index: 564337 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5050. Min Act: -0.0001

Data Index: 429300 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5043. Min Act: -0.0001

Data Index: 241748 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5223. Min Act: -0.0001

Data Index: 907740 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5382. Min Act: -0.0001

Data Index: 986471 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5592. Min Act: -0.0001

Data Index: 439524 (C4 (Web Text))

Max Activating Token Index: 930