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

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

Neuron 1501 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8962. Min Act: -0.0000

Data Index: 565045 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8561. Min Act: -0.0001

Data Index: 981829 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8979. Min Act: -0.0000

Data Index: 550745 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8335. Min Act: -0.0000

Data Index: 863915 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8557. Min Act: -0.0000

Data Index: 119283 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8279. Min Act: -0.0000

Data Index: 704975 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8515. Min Act: -0.0001

Data Index: 1060047 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7973. Min Act: -0.0000

Data Index: 142897 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7420. Min Act: -0.0000

Data Index: 342718 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6685. Min Act: -0.0000

Data Index: 624367 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7548. Min Act: -0.0000

Data Index: 801663 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6797. Min Act: -0.0000

Data Index: 131837 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7485. Min Act: -0.0001

Data Index: 304581 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7197. Min Act: -0.0000

Data Index: 221246 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7161. Min Act: -0.0000

Data Index: 810501 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6463. Min Act: -0.0000

Data Index: 942945 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7487. Min Act: -0.0000

Data Index: 1297538 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7614. Min Act: -0.0001

Data Index: 1177396 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1003821 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7500. Min Act: -0.0001

Data Index: 88112 (C4 (Web Text))

Max Activating Token Index: 847