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

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

Neuron 2839 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0860. Min Range: -2.0860

Max Act: 2.0860. Min Act: -0.0000

Data Index: 553244 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 2.0860. Min Range: -2.0860

Max Act: 1.8432. Min Act: -0.0000

Data Index: 1271313 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 2.0860. Min Range: -2.0860

Max Act: 1.7654. Min Act: -0.0000

Data Index: 192850 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 2.0860. Min Range: -2.0860

Max Act: 1.9100. Min Act: -0.0001

Data Index: 1238606 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 2.0860. Min Range: -2.0860

Max Act: 1.9538. Min Act: -0.0000

Data Index: 837251 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 2.0860. Min Range: -2.0860

Max Act: 1.7755. Min Act: -0.0000

Data Index: 107943 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 2.0860. Min Range: -2.0860

Max Act: 1.6933. Min Act: -0.0000

Data Index: 327329 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 2.0860. Min Range: -2.0860

Max Act: 1.7365. Min Act: -0.0000

Data Index: 1214042 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 2.0860. Min Range: -2.0860

Max Act: 1.7074. Min Act: -0.0000

Data Index: 428712 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 2.0860. Min Range: -2.0860

Max Act: 1.7080. Min Act: -0.0000

Data Index: 1064845 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 2.0860. Min Range: -2.0860

Max Act: 1.6054. Min Act: -0.0001

Data Index: 423938 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 2.0860. Min Range: -2.0860

Max Act: 1.7898. Min Act: -0.0000

Data Index: 1346489 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 2.0860. Min Range: -2.0860

Max Act: 1.6428. Min Act: -0.0000

Data Index: 750744 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 2.0860. Min Range: -2.0860

Max Act: 1.5357. Min Act: -0.0000

Data Index: 500873 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 2.0860. Min Range: -2.0860

Max Act: 1.5729. Min Act: -0.0000

Data Index: 496756 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 2.0860. Min Range: -2.0860

Max Act: 1.6381. Min Act: -0.0000

Data Index: 1306746 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 2.0860. Min Range: -2.0860

Max Act: 1.7287. Min Act: -0.0000

Data Index: 379148 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 2.0860. Min Range: -2.0860

Max Act: 1.5364. Min Act: -0.0000

Data Index: 703167 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 2.0860. Min Range: -2.0860

Max Act: 1.5617. Min Act: -0.0000

Data Index: 1276745 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 2.0860. Min Range: -2.0860

Max Act: 1.5332. Min Act: -0.0000

Data Index: 468791 (C4 (Web Text))

Max Activating Token Index: 905