Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1147 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.5702. Min Range: -2.5702

Max Act: 2.4384. Min Act: -0.0000

Data Index: 42220 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 2.5702. Min Range: -2.5702

Max Act: 2.5566. Min Act: -0.0000

Data Index: 554232 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 2.5702. Min Range: -2.5702

Max Act: 2.5702. Min Act: -0.0000

Data Index: 784390 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 2.5702. Min Range: -2.5702

Max Act: 2.2187. Min Act: -0.0000

Data Index: 797202 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 2.5702. Min Range: -2.5702

Max Act: 1.9846. Min Act: -0.0000

Data Index: 543131 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 2.5702. Min Range: -2.5702

Max Act: 2.0992. Min Act: -0.0000

Data Index: 938421 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 2.5702. Min Range: -2.5702

Max Act: 2.0121. Min Act: -0.0000

Data Index: 149607 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 2.5702. Min Range: -2.5702

Max Act: 2.1181. Min Act: -0.0000

Data Index: 355129 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 2.5702. Min Range: -2.5702

Max Act: 1.8820. Min Act: -0.0001

Data Index: 144631 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 2.5702. Min Range: -2.5702

Max Act: 1.8435. Min Act: -0.0000

Data Index: 335162 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 2.5702. Min Range: -2.5702

Max Act: 1.6133. Min Act: -0.0000

Data Index: 1031066 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 2.5702. Min Range: -2.5702

Max Act: 2.1535. Min Act: -0.0000

Data Index: 909563 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 2.5702. Min Range: -2.5702

Max Act: 1.7450. Min Act: -0.0000

Data Index: 440233 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 2.5702. Min Range: -2.5702

Max Act: 1.8376. Min Act: -0.0000

Data Index: 1341964 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 2.5702. Min Range: -2.5702

Max Act: 1.7055. Min Act: -0.0000

Data Index: 126454 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 2.5702. Min Range: -2.5702

Max Act: 1.7604. Min Act: -0.0001

Data Index: 982762 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 2.5702. Min Range: -2.5702

Max Act: 1.8892. Min Act: -0.0000

Data Index: 344461 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 2.5702. Min Range: -2.5702

Max Act: 1.8631. Min Act: -0.0000

Data Index: 306312 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 2.5702. Min Range: -2.5702

Max Act: 1.7410. Min Act: -0.0000

Data Index: 3402 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 2.5702. Min Range: -2.5702

Max Act: 1.7270. Min Act: -0.0000

Data Index: 755096 (C4 (Web Text))

Max Activating Token Index: 38