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

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

Neuron 4207 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.9207. Min Act: -0.0000

Data Index: 422098 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.8425. Min Act: -0.0000

Data Index: 326517 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.7855. Min Act: -0.0000

Data Index: 60159 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.8010. Min Act: -0.0000

Data Index: 971457 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.7498. Min Act: -0.0001

Data Index: 339097 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.7685. Min Act: -0.0000

Data Index: 886601 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.7544. Min Act: -0.0000

Data Index: 213070 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.6481. Min Act: -0.0000

Data Index: 735119 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.6423. Min Act: -0.0000

Data Index: 1231572 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.6953. Min Act: -0.0000

Data Index: 670482 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.6814. Min Act: -0.0000

Data Index: 1059634 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.7132. Min Act: -0.0001

Data Index: 602576 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.6777. Min Act: -0.0000

Data Index: 98891 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.6290. Min Act: -0.0000

Data Index: 1133813 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.6088. Min Act: -0.0001

Data Index: 81309 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1345830 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.6150. Min Act: -0.0000

Data Index: 297850 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.6522. Min Act: -0.0000

Data Index: 183403 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.6551. Min Act: -0.0000

Data Index: 1136598 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.6259. Min Act: -0.0000

Data Index: 885029 (C4 (Web Text))

Max Activating Token Index: 829