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

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

Neuron 393 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: 1.5426. Min Range: -1.5426

Max Act: 1.5426. Min Act: -0.0001

Data Index: 1044088 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.4112. Min Act: -0.0001

Data Index: 1304858 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.2215. Min Act: -0.0001

Data Index: 1280114 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.1981. Min Act: -0.0001

Data Index: 748251 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.1333. Min Act: -0.0001

Data Index: 682829 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.1939. Min Act: -0.0001

Data Index: 55170 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.1759. Min Act: -0.0001

Data Index: 1064541 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.1534. Min Act: -0.0001

Data Index: 377546 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.2296. Min Act: -0.0001

Data Index: 394866 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.0916. Min Act: -0.0001

Data Index: 798637 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.1845. Min Act: -0.0001

Data Index: 32544 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.1447. Min Act: -0.0001

Data Index: 670391 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.0030. Min Act: -0.0001

Data Index: 98476 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.0630. Min Act: -0.0001

Data Index: 1035561 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.1091. Min Act: -0.0001

Data Index: 942969 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.0122. Min Act: -0.0001

Data Index: 1195339 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.0464. Min Act: -0.0001

Data Index: 909747 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.0076. Min Act: -0.0001

Data Index: 921897 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.0073. Min Act: -0.0001

Data Index: 482058 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.0002. Min Act: -0.0001

Data Index: 621443 (C4 (Web Text))

Max Activating Token Index: 906