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

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

Neuron 2755 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: 2.3144. Min Range: -2.3144

Max Act: 2.3144. Min Act: -0.0000

Data Index: 917010 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 2.3144. Min Range: -2.3144

Max Act: 2.0451. Min Act: -0.0000

Data Index: 293549 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 2.3144. Min Range: -2.3144

Max Act: 1.8685. Min Act: -0.0000

Data Index: 74492 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 2.3144. Min Range: -2.3144

Max Act: 1.8245. Min Act: -0.0000

Data Index: 964182 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 2.3144. Min Range: -2.3144

Max Act: 1.5760. Min Act: -0.0000

Data Index: 833944 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 2.3144. Min Range: -2.3144

Max Act: 1.4772. Min Act: -0.0000

Data Index: 1314588 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 2.3144. Min Range: -2.3144

Max Act: 1.6500. Min Act: -0.0000

Data Index: 1276683 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 2.3144. Min Range: -2.3144

Max Act: 1.5371. Min Act: -0.0000

Data Index: 441511 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 2.3144. Min Range: -2.3144

Max Act: 1.5221. Min Act: -0.0000

Data Index: 1230882 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 2.3144. Min Range: -2.3144

Max Act: 1.4060. Min Act: -0.0000

Data Index: 1104311 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 2.3144. Min Range: -2.3144

Max Act: 1.4955. Min Act: -0.0000

Data Index: 4498 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 2.3144. Min Range: -2.3144

Max Act: 1.3993. Min Act: -0.0000

Data Index: 273198 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 2.3144. Min Range: -2.3144

Max Act: 1.3920. Min Act: -0.0000

Data Index: 470631 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 2.3144. Min Range: -2.3144

Max Act: 1.4709. Min Act: -0.0000

Data Index: 845584 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 2.3144. Min Range: -2.3144

Max Act: 1.5374. Min Act: -0.0000

Data Index: 546296 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 2.3144. Min Range: -2.3144

Max Act: 1.5049. Min Act: -0.0000

Data Index: 880700 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 2.3144. Min Range: -2.3144

Max Act: 1.3271. Min Act: -0.0000

Data Index: 688676 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 2.3144. Min Range: -2.3144

Max Act: 1.4055. Min Act: -0.0000

Data Index: 158313 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 2.3144. Min Range: -2.3144

Max Act: 1.4117. Min Act: -0.0000

Data Index: 872867 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 2.3144. Min Range: -2.3144

Max Act: 1.3982. Min Act: -0.0000

Data Index: 141292 (C4 (Web Text))

Max Activating Token Index: 995