Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2792 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.3527. Min Act: -0.0001

Data Index: 198662 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.3162. Min Act: -0.0001

Data Index: 1152850 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.3025. Min Act: -0.0001

Data Index: 303657 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.2692. Min Act: -0.0001

Data Index: 47747 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.2778. Min Act: -0.0001

Data Index: 1092276 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.2403. Min Act: -0.0001

Data Index: 71030 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.2483. Min Act: -0.0001

Data Index: 642829 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.2554. Min Act: -0.0001

Data Index: 794548 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.2423. Min Act: -0.0001

Data Index: 367337 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.2349. Min Act: -0.0001

Data Index: 317714 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.2411. Min Act: -0.0001

Data Index: 146088 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.2396. Min Act: -0.0001

Data Index: 241601 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.2154. Min Act: -0.0001

Data Index: 1239153 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.2287. Min Act: -0.0001

Data Index: 1615672 (Python Code)

Max Activating Token Index: 800

Text #14

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.2365. Min Act: -0.0001

Data Index: 796497 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.1929. Min Act: -0.0001

Data Index: 374491 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.2234. Min Act: -0.0001

Data Index: 442033 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.2304. Min Act: -0.0001

Data Index: 1450532 (Python Code)

Max Activating Token Index: 929

Text #18

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.2018. Min Act: -0.0001

Data Index: 92029 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.3527. Min Range: -0.3527

Max Act: 0.2067. Min Act: -0.0001

Data Index: 1650861 (Python Code)

Max Activating Token Index: 1001