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

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

Neuron 6019 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1845. Min Range: -2.1845

Max Act: 2.1845. Min Act: -0.0000

Data Index: 696951 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 2.1845. Min Range: -2.1845

Max Act: 1.8485. Min Act: 0.0000

Data Index: 425887 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 2.1845. Min Range: -2.1845

Max Act: 1.6156. Min Act: 0.0000

Data Index: 581591 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 2.1845. Min Range: -2.1845

Max Act: 1.8383. Min Act: -0.0000

Data Index: 1274820 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 2.1845. Min Range: -2.1845

Max Act: 1.5943. Min Act: -0.0000

Data Index: 524547 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 2.1845. Min Range: -2.1845

Max Act: 1.6943. Min Act: -0.0000

Data Index: 1203986 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 2.1845. Min Range: -2.1845

Max Act: 1.4982. Min Act: -0.0000

Data Index: 796406 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 2.1845. Min Range: -2.1845

Max Act: 1.4453. Min Act: -0.0000

Data Index: 1067351 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 2.1845. Min Range: -2.1845

Max Act: 1.4423. Min Act: -0.0000

Data Index: 30120 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 2.1845. Min Range: -2.1845

Max Act: 1.4375. Min Act: -0.0000

Data Index: 812476 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 2.1845. Min Range: -2.1845

Max Act: 1.4361. Min Act: 0.0000

Data Index: 35859 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 2.1845. Min Range: -2.1845

Max Act: 1.5069. Min Act: -0.0000

Data Index: 906796 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 2.1845. Min Range: -2.1845

Max Act: 1.4276. Min Act: -0.0000

Data Index: 1215053 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 2.1845. Min Range: -2.1845

Max Act: 1.4089. Min Act: -0.0000

Data Index: 788667 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 2.1845. Min Range: -2.1845

Max Act: 1.4124. Min Act: -0.0000

Data Index: 1287659 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 2.1845. Min Range: -2.1845

Max Act: 1.3897. Min Act: -0.0000

Data Index: 894498 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 2.1845. Min Range: -2.1845

Max Act: 1.3808. Min Act: -0.0000

Data Index: 1156929 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 2.1845. Min Range: -2.1845

Max Act: 1.3765. Min Act: -0.0000

Data Index: 725304 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 2.1845. Min Range: -2.1845

Max Act: 1.3825. Min Act: 0.0000

Data Index: 789238 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 2.1845. Min Range: -2.1845

Max Act: 1.3342. Min Act: -0.0000

Data Index: 1249609 (C4 (Web Text))

Max Activating Token Index: 152