Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4671 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8950. Min Range: -3.8950

Max Act: 3.8950. Min Act: -0.0000

Data Index: 868180 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 3.8950. Min Range: -3.8950

Max Act: 3.0532. Min Act: -0.0000

Data Index: 515116 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 3.8950. Min Range: -3.8950

Max Act: 3.0034. Min Act: -0.0000

Data Index: 1076154 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 3.8950. Min Range: -3.8950

Max Act: 3.1017. Min Act: -0.0000

Data Index: 373385 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 3.8950. Min Range: -3.8950

Max Act: 2.8398. Min Act: -0.0000

Data Index: 51270 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 3.8950. Min Range: -3.8950

Max Act: 3.0986. Min Act: -0.0000

Data Index: 648738 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 3.8950. Min Range: -3.8950

Max Act: 3.0474. Min Act: -0.0000

Data Index: 251035 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 3.8950. Min Range: -3.8950

Max Act: 2.9069. Min Act: -0.0000

Data Index: 697811 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 3.8950. Min Range: -3.8950

Max Act: 2.8067. Min Act: -0.0000

Data Index: 341069 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 3.8950. Min Range: -3.8950

Max Act: 2.7333. Min Act: -0.0000

Data Index: 310000 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 3.8950. Min Range: -3.8950

Max Act: 2.7194. Min Act: -0.0000

Data Index: 40235 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 3.8950. Min Range: -3.8950

Max Act: 2.6852. Min Act: -0.0000

Data Index: 1002317 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 3.8950. Min Range: -3.8950

Max Act: 2.8270. Min Act: -0.0000

Data Index: 812266 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 3.8950. Min Range: -3.8950

Max Act: 2.8040. Min Act: -0.0000

Data Index: 511096 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 3.8950. Min Range: -3.8950

Max Act: 2.5226. Min Act: -0.0000

Data Index: 595489 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 3.8950. Min Range: -3.8950

Max Act: 2.3534. Min Act: -0.0000

Data Index: 528825 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 3.8950. Min Range: -3.8950

Max Act: 2.7184. Min Act: -0.0000

Data Index: 526905 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 3.8950. Min Range: -3.8950

Max Act: 2.5582. Min Act: -0.0000

Data Index: 1137878 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 3.8950. Min Range: -3.8950

Max Act: 2.6785. Min Act: -0.0000

Data Index: 1232379 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 3.8950. Min Range: -3.8950

Max Act: 2.6757. Min Act: -0.0000

Data Index: 947133 (C4 (Web Text))

Max Activating Token Index: 392