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

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

Neuron 627 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: 0.9366. Min Range: -0.9366

Max Act: 0.8682. Min Act: -0.0002

Data Index: 686311 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.8583. Min Act: -0.0001

Data Index: 655764 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.9366. Min Act: -0.0002

Data Index: 966203 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.8874. Min Act: -0.0001

Data Index: 865239 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.8238. Min Act: -0.0002

Data Index: 1218666 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.7871. Min Act: -0.0002

Data Index: 935382 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.7753. Min Act: -0.0002

Data Index: 290214 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.7336. Min Act: -0.0002

Data Index: 484075 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.6705. Min Act: -0.0001

Data Index: 150127 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.7217. Min Act: -0.0001

Data Index: 817588 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.7201. Min Act: -0.0001

Data Index: 730914 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.7032. Min Act: -0.0001

Data Index: 953223 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.6708. Min Act: -0.0002

Data Index: 437921 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.7126. Min Act: -0.0001

Data Index: 617896 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.6821. Min Act: -0.0002

Data Index: 1190305 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.5799. Min Act: -0.0001

Data Index: 118662 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.6451. Min Act: -0.0002

Data Index: 1334441 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.6599. Min Act: -0.0002

Data Index: 33733 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.6768. Min Act: -0.0002

Data Index: 705847 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.6724. Min Act: -0.0001

Data Index: 653556 (C4 (Web Text))

Max Activating Token Index: 242