Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2613 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.7654. Min Act: -0.0000

Data Index: 288460 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.6886. Min Act: -0.0000

Data Index: 893612 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.6825. Min Act: -0.0000

Data Index: 416053 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.6016. Min Act: -0.0000

Data Index: 903775 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.5206. Min Act: -0.0000

Data Index: 164562 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.4721. Min Act: -0.0000

Data Index: 505257 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.5073. Min Act: -0.0000

Data Index: 681008 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.3275. Min Act: -0.0000

Data Index: 903816 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.3053. Min Act: -0.0000

Data Index: 214726 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.2430. Min Act: -0.0000

Data Index: 490139 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.1780. Min Act: -0.0000

Data Index: 631932 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.2425. Min Act: -0.0000

Data Index: 1339053 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.2251. Min Act: -0.0000

Data Index: 745232 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.2927. Min Act: -0.0000

Data Index: 1271407 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.2434. Min Act: -0.0000

Data Index: 311949 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.2336. Min Act: -0.0000

Data Index: 1231681 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.1657. Min Act: -0.0000

Data Index: 334584 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.1623. Min Act: -0.0000

Data Index: 1231097 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.1985. Min Act: -0.0000

Data Index: 767776 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 1.7654. Min Range: -1.7654

Max Act: 1.2117. Min Act: -0.0000

Data Index: 987248 (C4 (Web Text))

Max Activating Token Index: 703