Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 246 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.3742. Min Act: -0.0001

Data Index: 1119851 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.3790. Min Act: -0.0001

Data Index: 1060968 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.3287. Min Act: -0.0001

Data Index: 875602 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.3265. Min Act: -0.0001

Data Index: 573779 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.3120. Min Act: -0.0001

Data Index: 616744 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2995. Min Act: -0.0001

Data Index: 383952 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.3172. Min Act: -0.0001

Data Index: 749001 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.3260. Min Act: -0.0001

Data Index: 411565 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.3242. Min Act: -0.0001

Data Index: 365825 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.3136. Min Act: -0.0001

Data Index: 878568 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.3131. Min Act: -0.0001

Data Index: 238593 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.3348. Min Act: -0.0001

Data Index: 1140742 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2933. Min Act: -0.0001

Data Index: 1012728 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.3113. Min Act: -0.0001

Data Index: 344709 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.3111. Min Act: -0.0001

Data Index: 442017 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.3367. Min Act: -0.0001

Data Index: 575719 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2990. Min Act: -0.0001

Data Index: 45880 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.3079. Min Act: -0.0001

Data Index: 900478 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2888. Min Act: -0.0001

Data Index: 929446 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2945. Min Act: -0.0001

Data Index: 560458 (C4 (Web Text))

Max Activating Token Index: 932