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

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

Neuron 243 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: 1.0599. Min Range: -1.0599

Max Act: 1.0599. Min Act: -0.0001

Data Index: 1273940 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.9970. Min Act: -0.0001

Data Index: 1157570 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 1.0599. Min Range: -1.0599

Max Act: 1.0271. Min Act: -0.0001

Data Index: 143341 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.9683. Min Act: -0.0001

Data Index: 1161374 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.9660. Min Act: -0.0001

Data Index: 154208 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.9122. Min Act: -0.0001

Data Index: 277332 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8344. Min Act: -0.0001

Data Index: 846989 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8654. Min Act: -0.0001

Data Index: 945668 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8343. Min Act: -0.0001

Data Index: 121790 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8636. Min Act: -0.0001

Data Index: 229417 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7658. Min Act: -0.0001

Data Index: 114271 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8286. Min Act: -0.0001

Data Index: 995859 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8278. Min Act: -0.0001

Data Index: 728033 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8313. Min Act: -0.0001

Data Index: 1123988 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7731. Min Act: -0.0001

Data Index: 1004084 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7713. Min Act: -0.0001

Data Index: 260434 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7624. Min Act: -0.0001

Data Index: 686223 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7405. Min Act: -0.0001

Data Index: 645877 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7387. Min Act: -0.0001

Data Index: 676556 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7792. Min Act: -0.0001

Data Index: 657691 (C4 (Web Text))

Max Activating Token Index: 287