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

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

Neuron 1977 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7267. Min Range: -2.7267

Max Act: 2.7267. Min Act: -0.0000

Data Index: 58775 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 2.7267. Min Range: -2.7267

Max Act: 2.6898. Min Act: -0.0000

Data Index: 1221802 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 2.7267. Min Range: -2.7267

Max Act: 2.6493. Min Act: -0.0000

Data Index: 783623 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 2.7267. Min Range: -2.7267

Max Act: 2.3944. Min Act: -0.0000

Data Index: 1041238 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 2.7267. Min Range: -2.7267

Max Act: 2.5955. Min Act: -0.0000

Data Index: 267000 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 2.7267. Min Range: -2.7267

Max Act: 2.5020. Min Act: -0.0001

Data Index: 249459 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 2.7267. Min Range: -2.7267

Max Act: 2.4325. Min Act: -0.0000

Data Index: 1015548 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 2.7267. Min Range: -2.7267

Max Act: 2.4863. Min Act: -0.0000

Data Index: 1095857 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 2.7267. Min Range: -2.7267

Max Act: 2.2826. Min Act: -0.0000

Data Index: 197047 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 2.7267. Min Range: -2.7267

Max Act: 2.2469. Min Act: -0.0000

Data Index: 115297 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 2.7267. Min Range: -2.7267

Max Act: 2.0444. Min Act: -0.0001

Data Index: 707466 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 2.7267. Min Range: -2.7267

Max Act: 2.1460. Min Act: -0.0001

Data Index: 1161377 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 2.7267. Min Range: -2.7267

Max Act: 2.2228. Min Act: -0.0001

Data Index: 2192 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 2.7267. Min Range: -2.7267

Max Act: 2.0044. Min Act: -0.0001

Data Index: 234611 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 2.7267. Min Range: -2.7267

Max Act: 1.8766. Min Act: -0.0000

Data Index: 1103495 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 2.7267. Min Range: -2.7267

Max Act: 1.6871. Min Act: -0.0001

Data Index: 1594534 (Python Code)

Max Activating Token Index: 975

Text #16

Max Range: 2.7267. Min Range: -2.7267

Max Act: 1.7655. Min Act: -0.0000

Data Index: 619693 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 2.7267. Min Range: -2.7267

Max Act: 1.8156. Min Act: -0.0000

Data Index: 542373 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 2.7267. Min Range: -2.7267

Max Act: 1.9062. Min Act: -0.0001

Data Index: 36450 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 2.7267. Min Range: -2.7267

Max Act: 1.8526. Min Act: -0.0000

Data Index: 839448 (C4 (Web Text))

Max Activating Token Index: 47