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

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

Neuron 1303 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0085. Min Range: -5.0085

Max Act: 5.0085. Min Act: -0.0001

Data Index: 544975 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 5.0085. Min Range: -5.0085

Max Act: 4.7817. Min Act: -0.0001

Data Index: 1310869 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 5.0085. Min Range: -5.0085

Max Act: 4.9308. Min Act: -0.0001

Data Index: 1289133 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 5.0085. Min Range: -5.0085

Max Act: 4.9339. Min Act: -0.0001

Data Index: 28191 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 5.0085. Min Range: -5.0085

Max Act: 4.8799. Min Act: -0.0001

Data Index: 304413 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 5.0085. Min Range: -5.0085

Max Act: 4.8643. Min Act: -0.0001

Data Index: 524461 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 5.0085. Min Range: -5.0085

Max Act: 4.8176. Min Act: -0.0001

Data Index: 662749 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 5.0085. Min Range: -5.0085

Max Act: 4.7460. Min Act: -0.0001

Data Index: 346744 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 5.0085. Min Range: -5.0085

Max Act: 4.4835. Min Act: -0.0001

Data Index: 226889 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 5.0085. Min Range: -5.0085

Max Act: 4.3898. Min Act: -0.0001

Data Index: 758716 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 5.0085. Min Range: -5.0085

Max Act: 4.4832. Min Act: -0.0001

Data Index: 756674 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 5.0085. Min Range: -5.0085

Max Act: 4.4738. Min Act: -0.0001

Data Index: 882820 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 5.0085. Min Range: -5.0085

Max Act: 4.3895. Min Act: -0.0001

Data Index: 1249110 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 5.0085. Min Range: -5.0085

Max Act: 4.1779. Min Act: -0.0001

Data Index: 1258740 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 5.0085. Min Range: -5.0085

Max Act: 4.2468. Min Act: -0.0001

Data Index: 361152 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 5.0085. Min Range: -5.0085

Max Act: 4.2243. Min Act: -0.0001

Data Index: 1152764 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 5.0085. Min Range: -5.0085

Max Act: 4.2236. Min Act: -0.0001

Data Index: 342753 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 5.0085. Min Range: -5.0085

Max Act: 4.1497. Min Act: -0.0001

Data Index: 168274 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 5.0085. Min Range: -5.0085

Max Act: 3.9709. Min Act: -0.0001

Data Index: 496718 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 5.0085. Min Range: -5.0085

Max Act: 4.1020. Min Act: -0.0001

Data Index: 1251740 (C4 (Web Text))

Max Activating Token Index: 495