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

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

Neuron 543 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5929. Min Range: -3.5929

Max Act: 3.5929. Min Act: -0.0001

Data Index: 644565 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 3.5929. Min Range: -3.5929

Max Act: 3.5909. Min Act: -0.0001

Data Index: 849314 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 3.5929. Min Range: -3.5929

Max Act: 3.2987. Min Act: -0.0001

Data Index: 668219 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 3.5929. Min Range: -3.5929

Max Act: 3.1913. Min Act: -0.0000

Data Index: 1012944 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 3.5929. Min Range: -3.5929

Max Act: 3.1571. Min Act: -0.0000

Data Index: 415135 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 3.5929. Min Range: -3.5929

Max Act: 3.1285. Min Act: -0.0000

Data Index: 693961 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.9896. Min Act: -0.0000

Data Index: 1053550 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.6290. Min Act: -0.0000

Data Index: 14534 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.5900. Min Act: -0.0000

Data Index: 606503 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.4053. Min Act: -0.0000

Data Index: 74834 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.5340. Min Act: -0.0001

Data Index: 609223 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.5187. Min Act: -0.0000

Data Index: 13169 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.1774. Min Act: -0.0001

Data Index: 496797 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.3595. Min Act: -0.0000

Data Index: 1220566 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.3301. Min Act: -0.0001

Data Index: 155930 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.2005. Min Act: -0.0001

Data Index: 1093636 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.1585. Min Act: -0.0000

Data Index: 5659 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.1188. Min Act: -0.0001

Data Index: 191012 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.0943. Min Act: -0.0000

Data Index: 428157 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.1105. Min Act: -0.0000

Data Index: 332534 (C4 (Web Text))

Max Activating Token Index: 1016