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

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

Neuron 155 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8374. Min Range: -1.8374

Max Act: 1.8374. Min Act: -0.0000

Data Index: 1024230 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 1.8374. Min Range: -1.8374

Max Act: 1.7658. Min Act: -0.0000

Data Index: 785081 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 1.8374. Min Range: -1.8374

Max Act: 1.6226. Min Act: -0.0000

Data Index: 215060 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 1.8374. Min Range: -1.8374

Max Act: 1.7244. Min Act: -0.0000

Data Index: 1155715 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 1.8374. Min Range: -1.8374

Max Act: 1.6833. Min Act: -0.0000

Data Index: 1238455 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 1.8374. Min Range: -1.8374

Max Act: 1.6387. Min Act: -0.0000

Data Index: 101918 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 1.8374. Min Range: -1.8374

Max Act: 1.5938. Min Act: -0.0000

Data Index: 244790 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 1.8374. Min Range: -1.8374

Max Act: 1.5535. Min Act: -0.0000

Data Index: 1301704 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 1.8374. Min Range: -1.8374

Max Act: 1.4543. Min Act: -0.0000

Data Index: 1081922 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 1.8374. Min Range: -1.8374

Max Act: 1.5630. Min Act: -0.0000

Data Index: 1309602 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 1.8374. Min Range: -1.8374

Max Act: 1.4499. Min Act: -0.0000

Data Index: 1103983 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 1.8374. Min Range: -1.8374

Max Act: 1.4823. Min Act: -0.0000

Data Index: 1345837 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 1.8374. Min Range: -1.8374

Max Act: 1.5019. Min Act: -0.0000

Data Index: 864757 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 1.8374. Min Range: -1.8374

Max Act: 1.2642. Min Act: -0.0000

Data Index: 1500376 (Python Code)

Max Activating Token Index: 495

Text #14

Max Range: 1.8374. Min Range: -1.8374

Max Act: 1.4154. Min Act: -0.0000

Data Index: 51759 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 1.8374. Min Range: -1.8374

Max Act: 1.4137. Min Act: -0.0000

Data Index: 811114 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 1.8374. Min Range: -1.8374

Max Act: 1.4089. Min Act: -0.0000

Data Index: 1225891 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 1.8374. Min Range: -1.8374

Max Act: 1.2932. Min Act: -0.0000

Data Index: 161493 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 1.8374. Min Range: -1.8374

Max Act: 1.3013. Min Act: -0.0000

Data Index: 1208166 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 1.8374. Min Range: -1.8374

Max Act: 1.3762. Min Act: -0.0000

Data Index: 1270827 (C4 (Web Text))

Max Activating Token Index: 446