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

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

Neuron 3171 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: 1.1770. Min Range: -1.1770

Max Act: 1.1770. Min Act: -0.0001

Data Index: 762245 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 1.1770. Min Range: -1.1770

Max Act: 1.0708. Min Act: -0.0001

Data Index: 621802 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.9590. Min Act: -0.0001

Data Index: 1188095 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.9136. Min Act: -0.0001

Data Index: 145311 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8786. Min Act: -0.0001

Data Index: 693550 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8835. Min Act: -0.0001

Data Index: 334113 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.9070. Min Act: -0.0001

Data Index: 1315106 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8703. Min Act: -0.0001

Data Index: 1244965 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8597. Min Act: -0.0001

Data Index: 1050912 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8861. Min Act: -0.0001

Data Index: 204070 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8478. Min Act: -0.0001

Data Index: 376285 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8414. Min Act: -0.0001

Data Index: 601888 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8524. Min Act: -0.0001

Data Index: 234318 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8885. Min Act: -0.0001

Data Index: 450028 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8585. Min Act: -0.0001

Data Index: 1023638 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8428. Min Act: -0.0001

Data Index: 335243 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8382. Min Act: -0.0001

Data Index: 323340 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8887. Min Act: -0.0001

Data Index: 192342 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8548. Min Act: -0.0001

Data Index: 284809 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8544. Min Act: -0.0001

Data Index: 1043456 (C4 (Web Text))

Max Activating Token Index: 440