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

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

Neuron 893 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.4905. Min Act: -0.0001

Data Index: 890748 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.2824. Min Act: -0.0001

Data Index: 63207 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.4043. Min Act: -0.0001

Data Index: 1010385 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.2455. Min Act: -0.0001

Data Index: 633934 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.2450. Min Act: -0.0001

Data Index: 986288 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.2481. Min Act: -0.0001

Data Index: 657640 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.2333. Min Act: -0.0001

Data Index: 1241287 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.3694. Min Act: -0.0001

Data Index: 422249 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.2271. Min Act: -0.0001

Data Index: 665837 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.3613. Min Act: -0.0001

Data Index: 142852 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.3555. Min Act: -0.0001

Data Index: 939211 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.3313. Min Act: -0.0001

Data Index: 760066 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.3114. Min Act: -0.0001

Data Index: 1140968 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.1433. Min Act: -0.0001

Data Index: 1113921 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.2822. Min Act: -0.0001

Data Index: 392029 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.4586. Min Act: -0.0001

Data Index: 202890 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.2793. Min Act: -0.0001

Data Index: 113997 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.2854. Min Act: -0.0001

Data Index: 1261190 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.1256. Min Act: -0.0001

Data Index: 1225842 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.2718. Min Act: -0.0001

Data Index: 597443 (C4 (Web Text))

Max Activating Token Index: 977