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

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

Neuron 2898 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: 0.2976. Min Range: -0.2976

Max Act: 0.2815. Min Act: -0.0000

Data Index: 38794 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2976. Min Act: -0.0000

Data Index: 648781 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2532. Min Act: -0.0000

Data Index: 476884 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2417. Min Act: -0.0001

Data Index: 939439 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1048081 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2344. Min Act: -0.0000

Data Index: 374175 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2163. Min Act: -0.0000

Data Index: 630637 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2214. Min Act: -0.0001

Data Index: 520783 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2284. Min Act: -0.0000

Data Index: 420535 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2280. Min Act: -0.0001

Data Index: 213752 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2276. Min Act: -0.0000

Data Index: 659175 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2137. Min Act: -0.0001

Data Index: 1154744 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2416. Min Act: -0.0000

Data Index: 389898 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2124. Min Act: -0.0000

Data Index: 284461 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2176. Min Act: -0.0001

Data Index: 756164 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2018. Min Act: -0.0001

Data Index: 60114 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2043. Min Act: -0.0001

Data Index: 1262715 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2117. Min Act: -0.0000

Data Index: 270031 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1299894 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2013. Min Act: -0.0000

Data Index: 1116285 (C4 (Web Text))

Max Activating Token Index: 868