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

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

Neuron 20 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: 0.8075. Min Range: -0.8075

Max Act: 0.8075. Min Act: -0.0001

Data Index: 102674 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6386. Min Act: -0.0001

Data Index: 750084 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5913. Min Act: -0.0001

Data Index: 993968 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6227. Min Act: -0.0001

Data Index: 434035 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5967. Min Act: -0.0001

Data Index: 125181 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5901. Min Act: -0.0001

Data Index: 58860 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5495. Min Act: -0.0001

Data Index: 285672 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6077. Min Act: -0.0001

Data Index: 433148 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5280. Min Act: -0.0001

Data Index: 608918 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5458. Min Act: -0.0001

Data Index: 497879 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5540. Min Act: -0.0001

Data Index: 165052 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5512. Min Act: -0.0001

Data Index: 891491 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5447. Min Act: -0.0001

Data Index: 235545 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5157. Min Act: -0.0001

Data Index: 1274921 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5326. Min Act: -0.0001

Data Index: 1259059 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.4940. Min Act: -0.0001

Data Index: 555945 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5385. Min Act: -0.0001

Data Index: 1091921 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.4671. Min Act: -0.0001

Data Index: 983851 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.4982. Min Act: -0.0001

Data Index: 407102 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5305. Min Act: -0.0001

Data Index: 315720 (C4 (Web Text))

Max Activating Token Index: 705