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

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

Neuron 1917 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: 1.0448. Min Range: -1.0448

Max Act: 1.0444. Min Act: -0.0001

Data Index: 176117 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 1.0448. Min Range: -1.0448

Max Act: 1.0448. Min Act: -0.0001

Data Index: 1240810 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9591. Min Act: -0.0001

Data Index: 1310999 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9897. Min Act: -0.0001

Data Index: 1286294 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9073. Min Act: -0.0001

Data Index: 747009 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9584. Min Act: -0.0001

Data Index: 484962 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9309. Min Act: -0.0001

Data Index: 1348162 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8953. Min Act: -0.0001

Data Index: 944731 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9244. Min Act: -0.0001

Data Index: 168167 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9156. Min Act: -0.0001

Data Index: 963790 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8940. Min Act: -0.0001

Data Index: 1097247 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9131. Min Act: -0.0001

Data Index: 1346246 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8849. Min Act: -0.0001

Data Index: 1258771 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8474. Min Act: -0.0001

Data Index: 280586 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8747. Min Act: -0.0001

Data Index: 633636 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8467. Min Act: -0.0001

Data Index: 522976 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8441. Min Act: -0.0001

Data Index: 935365 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8448. Min Act: -0.0001

Data Index: 1253131 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8660. Min Act: -0.0001

Data Index: 4696 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8695. Min Act: -0.0001

Data Index: 855589 (C4 (Web Text))

Max Activating Token Index: 440