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

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

Neuron 2672 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2104. Min Range: -1.2104

Max Act: 1.2104. Min Act: -0.0001

Data Index: 593843 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 1.2104. Min Range: -1.2104

Max Act: 0.9300. Min Act: -0.0001

Data Index: 1306613 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 1.2104. Min Range: -1.2104

Max Act: 0.9130. Min Act: -0.0001

Data Index: 205507 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 1.2104. Min Range: -1.2104

Max Act: 0.9451. Min Act: -0.0001

Data Index: 31494 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 1.2104. Min Range: -1.2104

Max Act: 0.9145. Min Act: -0.0001

Data Index: 781714 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 1.2104. Min Range: -1.2104

Max Act: 0.9385. Min Act: -0.0001

Data Index: 1254115 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 1.2104. Min Range: -1.2104

Max Act: 0.9020. Min Act: -0.0001

Data Index: 1548027 (Python Code)

Max Activating Token Index: 827

Text #7

Max Range: 1.2104. Min Range: -1.2104

Max Act: 0.8995. Min Act: -0.0001

Data Index: 1220802 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 1.2104. Min Range: -1.2104

Max Act: 0.8394. Min Act: -0.0001

Data Index: 262436 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 1.2104. Min Range: -1.2104

Max Act: 0.8242. Min Act: -0.0001

Data Index: 994390 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 1.2104. Min Range: -1.2104

Max Act: 0.8475. Min Act: -0.0001

Data Index: 546999 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 1.2104. Min Range: -1.2104

Max Act: 0.7620. Min Act: -0.0001

Data Index: 297977 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 1.2104. Min Range: -1.2104

Max Act: 0.7552. Min Act: -0.0001

Data Index: 748053 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 1.2104. Min Range: -1.2104

Max Act: 0.7729. Min Act: -0.0001

Data Index: 1039164 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 1.2104. Min Range: -1.2104

Max Act: 0.8173. Min Act: -0.0001

Data Index: 356316 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 1.2104. Min Range: -1.2104

Max Act: 0.7580. Min Act: -0.0001

Data Index: 888744 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 1.2104. Min Range: -1.2104

Max Act: 0.7583. Min Act: -0.0001

Data Index: 646914 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 1.2104. Min Range: -1.2104

Max Act: 0.7278. Min Act: -0.0001

Data Index: 399374 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 1.2104. Min Range: -1.2104

Max Act: 0.7728. Min Act: -0.0001

Data Index: 654182 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 1.2104. Min Range: -1.2104

Max Act: 0.7070. Min Act: -0.0001

Data Index: 1629553 (Python Code)

Max Activating Token Index: 685