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

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

Neuron 3267 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.3348. Min Range: -2.3348

Max Act: 2.3348. Min Act: -0.0000

Data Index: 61496 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 2.3348. Min Range: -2.3348

Max Act: 2.2786. Min Act: -0.0001

Data Index: 909758 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 2.3348. Min Range: -2.3348

Max Act: 2.1492. Min Act: -0.0000

Data Index: 889475 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 2.3348. Min Range: -2.3348

Max Act: 1.9048. Min Act: -0.0000

Data Index: 1027468 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 2.3348. Min Range: -2.3348

Max Act: 1.9767. Min Act: -0.0000

Data Index: 666224 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 2.3348. Min Range: -2.3348

Max Act: 2.0820. Min Act: -0.0000

Data Index: 323012 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 2.3348. Min Range: -2.3348

Max Act: 1.8129. Min Act: -0.0001

Data Index: 911633 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 2.3348. Min Range: -2.3348

Max Act: 1.9194. Min Act: -0.0001

Data Index: 537811 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 2.3348. Min Range: -2.3348

Max Act: 1.8840. Min Act: -0.0001

Data Index: 716137 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 2.3348. Min Range: -2.3348

Max Act: 1.6555. Min Act: -0.0001

Data Index: 496813 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 2.3348. Min Range: -2.3348

Max Act: 1.8242. Min Act: -0.0000

Data Index: 1001135 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 2.3348. Min Range: -2.3348

Max Act: 1.6096. Min Act: -0.0000

Data Index: 964356 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 2.3348. Min Range: -2.3348

Max Act: 1.5900. Min Act: -0.0000

Data Index: 1188740 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 2.3348. Min Range: -2.3348

Max Act: 1.7876. Min Act: -0.0001

Data Index: 1202511 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 2.3348. Min Range: -2.3348

Max Act: 1.5803. Min Act: -0.0000

Data Index: 529939 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 2.3348. Min Range: -2.3348

Max Act: 1.4667. Min Act: -0.0000

Data Index: 594136 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 2.3348. Min Range: -2.3348

Max Act: 1.5824. Min Act: -0.0000

Data Index: 1353778 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 2.3348. Min Range: -2.3348

Max Act: 1.5322. Min Act: -0.0000

Data Index: 1255592 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 2.3348. Min Range: -2.3348

Max Act: 1.6125. Min Act: -0.0000

Data Index: 1151340 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 2.3348. Min Range: -2.3348

Max Act: 1.3942. Min Act: -0.0000

Data Index: 51440 (C4 (Web Text))

Max Activating Token Index: 927