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

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

Neuron 2944 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.5162. Min Act: -0.0001

Data Index: 523403 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4514. Min Act: -0.0002

Data Index: 426972 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4525. Min Act: -0.0001

Data Index: 123368 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4272. Min Act: -0.0001

Data Index: 591663 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4545. Min Act: -0.0002

Data Index: 641342 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4328. Min Act: -0.0001

Data Index: 618759 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4139. Min Act: -0.0001

Data Index: 667801 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4209. Min Act: -0.0001

Data Index: 270624 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4226. Min Act: -0.0001

Data Index: 858704 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4343. Min Act: -0.0002

Data Index: 194111 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4085. Min Act: -0.0001

Data Index: 352297 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4025. Min Act: -0.0001

Data Index: 1304001 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4125. Min Act: -0.0001

Data Index: 424046 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4264. Min Act: -0.0001

Data Index: 376782 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4103. Min Act: -0.0001

Data Index: 1265746 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.3974. Min Act: -0.0001

Data Index: 264041 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4370. Min Act: -0.0002

Data Index: 955609 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4048. Min Act: -0.0001

Data Index: 4561 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.3876. Min Act: -0.0001

Data Index: 182688 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4004. Min Act: -0.0001

Data Index: 253975 (C4 (Web Text))

Max Activating Token Index: 100