Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3218 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8457. Min Range: -1.8457

Max Act: 1.8018. Min Act: -0.0001

Data Index: 396763 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 1.8457. Min Range: -1.8457

Max Act: 1.8271. Min Act: -0.0001

Data Index: 280337 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 1.8457. Min Range: -1.8457

Max Act: 1.7322. Min Act: -0.0001

Data Index: 438340 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 1.8457. Min Range: -1.8457

Max Act: 1.6029. Min Act: -0.0001

Data Index: 1093417 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 1.8457. Min Range: -1.8457

Max Act: 1.8104. Min Act: -0.0001

Data Index: 1088913 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 1.8457. Min Range: -1.8457

Max Act: 1.8017. Min Act: -0.0001

Data Index: 1096096 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 1.8457. Min Range: -1.8457

Max Act: 1.8021. Min Act: -0.0001

Data Index: 216527 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 1.8457. Min Range: -1.8457

Max Act: 1.7268. Min Act: -0.0001

Data Index: 284788 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 1.8457. Min Range: -1.8457

Max Act: 1.6736. Min Act: -0.0001

Data Index: 159843 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 1.8457. Min Range: -1.8457

Max Act: 1.7203. Min Act: -0.0001

Data Index: 407625 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 1.8457. Min Range: -1.8457

Max Act: 1.6213. Min Act: -0.0001

Data Index: 180049 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 1.8457. Min Range: -1.8457

Max Act: 1.8457. Min Act: -0.0001

Data Index: 776073 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 1.8457. Min Range: -1.8457

Max Act: 1.6697. Min Act: -0.0001

Data Index: 227374 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 1.8457. Min Range: -1.8457

Max Act: 1.6953. Min Act: -0.0001

Data Index: 1038788 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 1.8457. Min Range: -1.8457

Max Act: 1.6078. Min Act: -0.0001

Data Index: 612295 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 1.8457. Min Range: -1.8457

Max Act: 1.6788. Min Act: -0.0001

Data Index: 258858 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 1.8457. Min Range: -1.8457

Max Act: 1.5713. Min Act: -0.0001

Data Index: 328345 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 1.8457. Min Range: -1.8457

Max Act: 1.7630. Min Act: -0.0001

Data Index: 1220821 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 1.8457. Min Range: -1.8457

Max Act: 1.7053. Min Act: -0.0001

Data Index: 485922 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 1.8457. Min Range: -1.8457

Max Act: 1.5331. Min Act: -0.0001

Data Index: 954705 (C4 (Web Text))

Max Activating Token Index: 926