Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1678 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.6939. Min Act: -0.0003

Data Index: 687022 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.5841. Min Act: -0.0003

Data Index: 1129467 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.6015. Min Act: -0.0003

Data Index: 788536 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.5435. Min Act: -0.0003

Data Index: 898631 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.5305. Min Act: -0.0003

Data Index: 548902 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.5139. Min Act: -0.0003

Data Index: 949565 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4753. Min Act: -0.0003

Data Index: 748323 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4917. Min Act: -0.0003

Data Index: 1139708 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4768. Min Act: -0.0003

Data Index: 1117501 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4751. Min Act: -0.0003

Data Index: 565903 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4335. Min Act: -0.0003

Data Index: 1120575 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4416. Min Act: -0.0003

Data Index: 537785 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4191. Min Act: -0.0003

Data Index: 166216 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4314. Min Act: -0.0003

Data Index: 1337150 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4021. Min Act: -0.0003

Data Index: 153464 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4008. Min Act: -0.0003

Data Index: 397800 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4142. Min Act: -0.0003

Data Index: 180991 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4257. Min Act: -0.0003

Data Index: 896270 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4200. Min Act: -0.0003

Data Index: 288644 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4090. Min Act: -0.0003

Data Index: 1207420 (C4 (Web Text))

Max Activating Token Index: 313