Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1041 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4588. Min Range: -0.4588

Max Act: 0.4588. Min Act: -0.0001

Data Index: 608362 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 0.4588. Min Range: -0.4588

Max Act: 0.4478. Min Act: -0.0001

Data Index: 1126937 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 0.4588. Min Range: -0.4588

Max Act: 0.4380. Min Act: -0.0001

Data Index: 1016928 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.4588. Min Range: -0.4588

Max Act: 0.4008. Min Act: -0.0001

Data Index: 1154302 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 0.4588. Min Range: -0.4588

Max Act: 0.4267. Min Act: -0.0001

Data Index: 62317 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.4588. Min Range: -0.4588

Max Act: 0.4001. Min Act: -0.0001

Data Index: 806418 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.4588. Min Range: -0.4588

Max Act: 0.4239. Min Act: -0.0001

Data Index: 1324512 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.4588. Min Range: -0.4588

Max Act: 0.4086. Min Act: -0.0001

Data Index: 207892 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.4588. Min Range: -0.4588

Max Act: 0.4091. Min Act: -0.0001

Data Index: 1305916 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.4588. Min Range: -0.4588

Max Act: 0.4071. Min Act: -0.0001

Data Index: 488631 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.4588. Min Range: -0.4588

Max Act: 0.4046. Min Act: -0.0001

Data Index: 1241532 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.4588. Min Range: -0.4588

Max Act: 0.4054. Min Act: -0.0001

Data Index: 931431 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.4588. Min Range: -0.4588

Max Act: 0.4157. Min Act: -0.0001

Data Index: 1165211 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.4588. Min Range: -0.4588

Max Act: 0.3945. Min Act: -0.0001

Data Index: 1044655 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 0.4588. Min Range: -0.4588

Max Act: 0.4053. Min Act: -0.0001

Data Index: 1005197 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.4588. Min Range: -0.4588

Max Act: 0.4060. Min Act: -0.0001

Data Index: 1309430 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 0.4588. Min Range: -0.4588

Max Act: 0.4017. Min Act: -0.0001

Data Index: 223541 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 0.4588. Min Range: -0.4588

Max Act: 0.3995. Min Act: -0.0001

Data Index: 830960 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 0.4588. Min Range: -0.4588

Max Act: 0.3993. Min Act: -0.0001

Data Index: 1137154 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.4588. Min Range: -0.4588

Max Act: 0.3850. Min Act: -0.0001

Data Index: 392966 (C4 (Web Text))

Max Activating Token Index: 42