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

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

Neuron 3538 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.5885. Min Act: -0.0001

Data Index: 998973 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.4365. Min Act: -0.0001

Data Index: 977391 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.4874. Min Act: -0.0001

Data Index: 100175 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.4236. Min Act: -0.0001

Data Index: 787936 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.2983. Min Act: -0.0001

Data Index: 251174 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.3056. Min Act: -0.0001

Data Index: 1146978 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.3339. Min Act: -0.0001

Data Index: 275483 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.2973. Min Act: -0.0001

Data Index: 438948 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.1636. Min Act: -0.0001

Data Index: 271086 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.1673. Min Act: -0.0001

Data Index: 193943 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.1268. Min Act: -0.0001

Data Index: 494477 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.1881. Min Act: -0.0001

Data Index: 487177 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.1663. Min Act: -0.0001

Data Index: 1179716 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.0916. Min Act: -0.0001

Data Index: 1192462 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.0791. Min Act: -0.0001

Data Index: 597548 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.1365. Min Act: -0.0001

Data Index: 47745 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.1318. Min Act: -0.0001

Data Index: 476195 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.0459. Min Act: -0.0001

Data Index: 720140 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.0391. Min Act: -0.0001

Data Index: 675730 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.1203. Min Act: -0.0001

Data Index: 680772 (C4 (Web Text))

Max Activating Token Index: 769