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

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

Neuron 3018 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9203. Min Range: -2.9203

Max Act: 2.7190. Min Act: -0.0000

Data Index: 554971 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 2.9203. Min Range: -2.9203

Max Act: 2.9203. Min Act: -0.0000

Data Index: 798018 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 2.9203. Min Range: -2.9203

Max Act: 2.7627. Min Act: -0.0000

Data Index: 548569 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 2.9203. Min Range: -2.9203

Max Act: 2.8082. Min Act: -0.0000

Data Index: 686725 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 2.9203. Min Range: -2.9203

Max Act: 2.5047. Min Act: -0.0000

Data Index: 655449 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 2.9203. Min Range: -2.9203

Max Act: 2.2621. Min Act: -0.0000

Data Index: 404796 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 2.9203. Min Range: -2.9203

Max Act: 2.3459. Min Act: -0.0000

Data Index: 730880 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 2.9203. Min Range: -2.9203

Max Act: 2.5467. Min Act: -0.0000

Data Index: 226450 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 2.9203. Min Range: -2.9203

Max Act: 2.1532. Min Act: -0.0000

Data Index: 1241728 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 2.9203. Min Range: -2.9203

Max Act: 2.3563. Min Act: -0.0000

Data Index: 262556 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 2.9203. Min Range: -2.9203

Max Act: 2.3416. Min Act: -0.0000

Data Index: 827198 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 2.9203. Min Range: -2.9203

Max Act: 2.0591. Min Act: -0.0000

Data Index: 292212 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 2.9203. Min Range: -2.9203

Max Act: 2.2051. Min Act: -0.0000

Data Index: 745856 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 2.9203. Min Range: -2.9203

Max Act: 2.0798. Min Act: -0.0000

Data Index: 1058894 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 2.9203. Min Range: -2.9203

Max Act: 2.1020. Min Act: -0.0000

Data Index: 1255720 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 2.9203. Min Range: -2.9203

Max Act: 2.0704. Min Act: -0.0000

Data Index: 469430 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 2.9203. Min Range: -2.9203

Max Act: 2.0418. Min Act: -0.0000

Data Index: 556756 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 2.9203. Min Range: -2.9203

Max Act: 1.9129. Min Act: -0.0000

Data Index: 1227755 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 2.9203. Min Range: -2.9203

Max Act: 1.9170. Min Act: -0.0000

Data Index: 602369 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 2.9203. Min Range: -2.9203

Max Act: 1.7791. Min Act: -0.0000

Data Index: 1336448 (C4 (Web Text))

Max Activating Token Index: 152