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

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

Neuron 978 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: 1.3414. Min Range: -1.3414

Max Act: 1.3414. Min Act: -0.0001

Data Index: 1157682 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 1.3414. Min Range: -1.3414

Max Act: 1.2647. Min Act: -0.0001

Data Index: 938275 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 1.3414. Min Range: -1.3414

Max Act: 1.1680. Min Act: -0.0001

Data Index: 992466 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 1.3414. Min Range: -1.3414

Max Act: 1.1494. Min Act: -0.0001

Data Index: 497116 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 1.3414. Min Range: -1.3414

Max Act: 1.1277. Min Act: -0.0001

Data Index: 661493 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 1.3414. Min Range: -1.3414

Max Act: 0.9883. Min Act: -0.0001

Data Index: 603089 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 1.3414. Min Range: -1.3414

Max Act: 1.0765. Min Act: -0.0001

Data Index: 256933 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 1.3414. Min Range: -1.3414

Max Act: 1.0795. Min Act: -0.0001

Data Index: 734607 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 1.3414. Min Range: -1.3414

Max Act: 1.0681. Min Act: -0.0001

Data Index: 756103 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 1.3414. Min Range: -1.3414

Max Act: 1.0321. Min Act: -0.0001

Data Index: 462847 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 1.3414. Min Range: -1.3414

Max Act: 1.0390. Min Act: -0.0001

Data Index: 326111 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 1.3414. Min Range: -1.3414

Max Act: 1.0081. Min Act: -0.0001

Data Index: 1255483 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 1.3414. Min Range: -1.3414

Max Act: 0.9679. Min Act: -0.0001

Data Index: 600249 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 1.3414. Min Range: -1.3414

Max Act: 1.0457. Min Act: -0.0001

Data Index: 967531 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 1.3414. Min Range: -1.3414

Max Act: 0.9567. Min Act: -0.0001

Data Index: 1055017 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 1.3414. Min Range: -1.3414

Max Act: 0.9927. Min Act: -0.0001

Data Index: 512891 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 1.3414. Min Range: -1.3414

Max Act: 0.9562. Min Act: -0.0001

Data Index: 601623 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 1.3414. Min Range: -1.3414

Max Act: 0.9796. Min Act: -0.0001

Data Index: 501148 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 1.3414. Min Range: -1.3414

Max Act: 0.9774. Min Act: -0.0001

Data Index: 229033 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 1.3414. Min Range: -1.3414

Max Act: 0.9795. Min Act: -0.0001

Data Index: 951711 (C4 (Web Text))

Max Activating Token Index: 213