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

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

Neuron 2543 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.4443. Min Act: 0.0001

Data Index: 1108401 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3407. Min Act: -0.0000

Data Index: 909578 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3352. Min Act: -0.0000

Data Index: 708294 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3550. Min Act: -0.0000

Data Index: 478539 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3371. Min Act: -0.0001

Data Index: 563045 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1095368 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3164. Min Act: -0.0000

Data Index: 229025 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3122. Min Act: -0.0000

Data Index: 1172301 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3106. Min Act: -0.0000

Data Index: 472902 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.2990. Min Act: -0.0000

Data Index: 520294 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3076. Min Act: -0.0001

Data Index: 1088790 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.2950. Min Act: -0.0000

Data Index: 496153 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.2938. Min Act: -0.0000

Data Index: 995449 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3063. Min Act: -0.0000

Data Index: 578028 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3057. Min Act: -0.0000

Data Index: 357360 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.2939. Min Act: -0.0001

Data Index: 408006 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.2916. Min Act: -0.0000

Data Index: 527940 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.2999. Min Act: -0.0000

Data Index: 146778 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3060. Min Act: -0.0000

Data Index: 1232503 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.2759. Min Act: -0.0001

Data Index: 189161 (C4 (Web Text))

Max Activating Token Index: 167