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

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

Neuron 1585 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.9672. Min Act: -0.0001

Data Index: 1146381 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.9954. Min Act: -0.0001

Data Index: 1020753 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.9332. Min Act: -0.0001

Data Index: 314827 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.9451. Min Act: -0.0001

Data Index: 1172603 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.9020. Min Act: -0.0001

Data Index: 454147 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.8959. Min Act: -0.0001

Data Index: 1243861 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.9119. Min Act: -0.0001

Data Index: 419802 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.9310. Min Act: -0.0001

Data Index: 443834 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.8913. Min Act: -0.0001

Data Index: 1237276 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.8584. Min Act: -0.0001

Data Index: 852361 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.8057. Min Act: -0.0001

Data Index: 1131648 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.8866. Min Act: -0.0001

Data Index: 1272167 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.8565. Min Act: -0.0001

Data Index: 732525 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.8088. Min Act: -0.0001

Data Index: 398477 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.8469. Min Act: -0.0001

Data Index: 540930 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.8149. Min Act: -0.0001

Data Index: 1344183 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.7885. Min Act: -0.0001

Data Index: 693697 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.8163. Min Act: -0.0001

Data Index: 556081 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.8302. Min Act: -0.0001

Data Index: 94047 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.7913. Min Act: -0.0001

Data Index: 519024 (C4 (Web Text))

Max Activating Token Index: 858