Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 586 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.1751. Min Act: 0.0000

Data Index: 97185 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.2029. Min Act: -0.0000

Data Index: 511901 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.1097. Min Act: 0.0000

Data Index: 898550 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.0632. Min Act: 0.0000

Data Index: 537486 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.0404. Min Act: 0.0000

Data Index: 149146 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.0202. Min Act: -0.0000

Data Index: 25528 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9953. Min Act: -0.0000

Data Index: 1147546 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9821. Min Act: 0.0000

Data Index: 544749 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9561. Min Act: 0.0000

Data Index: 1324644 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9220. Min Act: -0.0000

Data Index: 371002 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8669. Min Act: 0.0000

Data Index: 112217 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8288. Min Act: -0.0000

Data Index: 1219533 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.7994. Min Act: -0.0000

Data Index: 540786 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.7773. Min Act: 0.0000

Data Index: 921139 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.7809. Min Act: 0.0000

Data Index: 912259 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.7759. Min Act: -0.0000

Data Index: 458290 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.7321. Min Act: 0.0000

Data Index: 235018 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.7565. Min Act: -0.0000

Data Index: 739705 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.7355. Min Act: 0.0000

Data Index: 647941 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.7320. Min Act: -0.0000

Data Index: 313384 (C4 (Web Text))

Max Activating Token Index: 257