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

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

Neuron 415 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: 3.4042. Min Range: -3.4042

Max Act: 3.4042. Min Act: -0.0000

Data Index: 196134 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.7632. Min Act: -0.0000

Data Index: 402246 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.1954. Min Act: -0.0000

Data Index: 1112288 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.4422. Min Act: -0.0000

Data Index: 803300 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.9005. Min Act: -0.0000

Data Index: 262344 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.3136. Min Act: -0.0000

Data Index: 480586 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.2786. Min Act: -0.0000

Data Index: 524582 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.2063. Min Act: -0.0000

Data Index: 312356 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 3.4042. Min Range: -3.4042

Max Act: 1.7334. Min Act: -0.0000

Data Index: 615473 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.1424. Min Act: -0.0000

Data Index: 185778 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 3.4042. Min Range: -3.4042

Max Act: 1.7966. Min Act: -0.0000

Data Index: 777915 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.0175. Min Act: -0.0000

Data Index: 39988 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 3.4042. Min Range: -3.4042

Max Act: 1.6597. Min Act: -0.0000

Data Index: 83125 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 3.4042. Min Range: -3.4042

Max Act: 1.8634. Min Act: -0.0000

Data Index: 55243 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 3.4042. Min Range: -3.4042

Max Act: 1.6688. Min Act: -0.0000

Data Index: 757515 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 3.4042. Min Range: -3.4042

Max Act: 1.7415. Min Act: -0.0000

Data Index: 658338 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 3.4042. Min Range: -3.4042

Max Act: 1.9328. Min Act: -0.0000

Data Index: 1327351 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 3.4042. Min Range: -3.4042

Max Act: 1.8274. Min Act: -0.0000

Data Index: 100126 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 3.4042. Min Range: -3.4042

Max Act: 1.5420. Min Act: -0.0000

Data Index: 644852 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 3.4042. Min Range: -3.4042

Max Act: 1.7450. Min Act: -0.0000

Data Index: 752348 (C4 (Web Text))

Max Activating Token Index: 59