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

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

Neuron 687 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: 1.2916. Min Range: -1.2916

Max Act: 1.1778. Min Act: -0.0001

Data Index: 406249 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.2916. Min Act: -0.0001

Data Index: 518697 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.1932. Min Act: -0.0001

Data Index: 551141 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.1320. Min Act: -0.0001

Data Index: 1189386 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.1940. Min Act: -0.0001

Data Index: 80505 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.0816. Min Act: -0.0001

Data Index: 401176 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.0718. Min Act: -0.0001

Data Index: 907624 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 1.2916. Min Range: -1.2916

Max Act: 0.9627. Min Act: -0.0001

Data Index: 668587 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.0338. Min Act: -0.0001

Data Index: 745325 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.1582. Min Act: -0.0001

Data Index: 1304933 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 1.2916. Min Range: -1.2916

Max Act: 0.9703. Min Act: -0.0001

Data Index: 1201518 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.0483. Min Act: -0.0001

Data Index: 799461 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 1.2916. Min Range: -1.2916

Max Act: 0.9942. Min Act: -0.0001

Data Index: 818787 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 1.2916. Min Range: -1.2916

Max Act: 0.9797. Min Act: -0.0001

Data Index: 721835 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 1.2916. Min Range: -1.2916

Max Act: 0.9946. Min Act: -0.0001

Data Index: 856004 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.0860. Min Act: -0.0001

Data Index: 181230 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 1.2916. Min Range: -1.2916

Max Act: 0.9893. Min Act: -0.0001

Data Index: 960296 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.0393. Min Act: -0.0001

Data Index: 153505 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 1.2916. Min Range: -1.2916

Max Act: 0.9693. Min Act: -0.0001

Data Index: 1250790 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 1.2916. Min Range: -1.2916

Max Act: 1.0174. Min Act: -0.0001

Data Index: 756668 (C4 (Web Text))

Max Activating Token Index: 925