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

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

Neuron 757 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.3513. Min Act: -0.0001

Data Index: 1281173 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.3456. Min Act: -0.0001

Data Index: 49176 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.2369. Min Act: -0.0001

Data Index: 609155 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.1035. Min Act: -0.0001

Data Index: 294501 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.1262. Min Act: -0.0001

Data Index: 518512 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.0828. Min Act: -0.0001

Data Index: 255311 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.1168. Min Act: -0.0001

Data Index: 544955 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.1289. Min Act: -0.0001

Data Index: 4190 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.0764. Min Act: -0.0001

Data Index: 441768 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.0538. Min Act: -0.0001

Data Index: 386574 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 1.3513. Min Range: -1.3513

Max Act: 0.9780. Min Act: -0.0001

Data Index: 753651 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 1.3513. Min Range: -1.3513

Max Act: 0.9929. Min Act: -0.0001

Data Index: 9382 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 1.3513. Min Range: -1.3513

Max Act: 1.0770. Min Act: -0.0001

Data Index: 626211 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 1.3513. Min Range: -1.3513

Max Act: 0.9828. Min Act: -0.0001

Data Index: 564010 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 1.3513. Min Range: -1.3513

Max Act: 0.9548. Min Act: -0.0001

Data Index: 774253 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 1.3513. Min Range: -1.3513

Max Act: 0.9408. Min Act: -0.0001

Data Index: 861202 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 1.3513. Min Range: -1.3513

Max Act: 0.9957. Min Act: -0.0001

Data Index: 385662 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 1.3513. Min Range: -1.3513

Max Act: 0.7763. Min Act: -0.0001

Data Index: 1221937 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 1.3513. Min Range: -1.3513

Max Act: 0.9269. Min Act: -0.0001

Data Index: 579504 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 1.3513. Min Range: -1.3513

Max Act: 0.8710. Min Act: -0.0001

Data Index: 1283741 (C4 (Web Text))

Max Activating Token Index: 377