Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2697 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.7090. Min Act: -0.0000

Data Index: 933085 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.7131. Min Act: -0.0000

Data Index: 1600731 (Python Code)

Max Activating Token Index: 969

Text #2

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.6898. Min Act: -0.0000

Data Index: 1471846 (Python Code)

Max Activating Token Index: 51

Text #3

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.6420. Min Act: -0.0000

Data Index: 1624727 (Python Code)

Max Activating Token Index: 628

Text #4

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.6465. Min Act: -0.0000

Data Index: 1418354 (Python Code)

Max Activating Token Index: 891

Text #5

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.6839. Min Act: -0.0000

Data Index: 34821 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.6049. Min Act: -0.0000

Data Index: 884573 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.6036. Min Act: -0.0000

Data Index: 1464725 (Python Code)

Max Activating Token Index: 541

Text #8

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1360867 (Python Code)

Max Activating Token Index: 92

Text #9

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1564238 (Python Code)

Max Activating Token Index: 395

Text #10

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.6159. Min Act: -0.0000

Data Index: 1336983 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.4706. Min Act: -0.0000

Data Index: 185020 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.4772. Min Act: -0.0000

Data Index: 634796 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1572115 (Python Code)

Max Activating Token Index: 758

Text #14

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.4897. Min Act: -0.0000

Data Index: 1353916 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.5065. Min Act: -0.0000

Data Index: 1426122 (Python Code)

Max Activating Token Index: 602

Text #16

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.4989. Min Act: -0.0000

Data Index: 1635715 (Python Code)

Max Activating Token Index: 659

Text #17

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.4536. Min Act: -0.0000

Data Index: 27151 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.4693. Min Act: -0.0000

Data Index: 1428411 (Python Code)

Max Activating Token Index: 129

Text #19

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.5192. Min Act: -0.0000

Data Index: 1449328 (Python Code)

Max Activating Token Index: 763