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

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

Neuron 3033 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: 0.5040. Min Range: -0.5040

Max Act: 0.5040. Min Act: -0.0001

Data Index: 481986 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4890. Min Act: -0.0001

Data Index: 57233 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4729. Min Act: -0.0001

Data Index: 845848 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4822. Min Act: -0.0001

Data Index: 486343 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4756. Min Act: -0.0001

Data Index: 1071073 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4862. Min Act: -0.0000

Data Index: 672675 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4545. Min Act: -0.0001

Data Index: 246725 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4517. Min Act: -0.0001

Data Index: 1258699 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4295. Min Act: -0.0001

Data Index: 66415 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4407. Min Act: -0.0000

Data Index: 654109 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.3848. Min Act: -0.0000

Data Index: 924619 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4576. Min Act: -0.0001

Data Index: 1053424 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4413. Min Act: -0.0001

Data Index: 1220645 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4300. Min Act: -0.0000

Data Index: 254585 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4053. Min Act: -0.0000

Data Index: 274873 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4133. Min Act: -0.0001

Data Index: 1182913 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.3999. Min Act: -0.0001

Data Index: 1301475 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4117. Min Act: -0.0000

Data Index: 426474 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4094. Min Act: -0.0001

Data Index: 986619 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 0.5040. Min Range: -0.5040

Max Act: 0.4251. Min Act: -0.0001

Data Index: 1144562 (C4 (Web Text))

Max Activating Token Index: 986