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

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

Neuron 2705 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.4591. Min Act: -0.0000

Data Index: 152918 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.9748. Min Act: -0.0000

Data Index: 417182 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.0091. Min Act: -0.0000

Data Index: 382291 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.0883. Min Act: -0.0000

Data Index: 326852 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.9835. Min Act: -0.0000

Data Index: 101525 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.0030. Min Act: -0.0000

Data Index: 671753 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.9287. Min Act: -0.0000

Data Index: 1040359 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.9773. Min Act: -0.0000

Data Index: 1274319 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.9550. Min Act: -0.0000

Data Index: 243108 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.9476. Min Act: -0.0000

Data Index: 840114 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.9205. Min Act: -0.0000

Data Index: 508648 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.8907. Min Act: -0.0000

Data Index: 1098741 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.9150. Min Act: -0.0000

Data Index: 858676 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.9314. Min Act: -0.0000

Data Index: 674562 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.8719. Min Act: -0.0000

Data Index: 602912 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.8773. Min Act: -0.0000

Data Index: 351913 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.8869. Min Act: -0.0000

Data Index: 165951 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.8794. Min Act: -0.0000

Data Index: 850640 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.8298. Min Act: -0.0000

Data Index: 1354907 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.8191. Min Act: -0.0000

Data Index: 117490 (C4 (Web Text))

Max Activating Token Index: 98