Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3704 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.5402. Min Act: -0.0000

Data Index: 907544 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1261063 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4030. Min Act: -0.0000

Data Index: 591208 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4238. Min Act: -0.0000

Data Index: 946324 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4220. Min Act: -0.0000

Data Index: 1022738 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3731. Min Act: -0.0000

Data Index: 43708 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3643. Min Act: -0.0000

Data Index: 241607 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3617. Min Act: -0.0000

Data Index: 573276 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3679. Min Act: -0.0000

Data Index: 1047914 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3445. Min Act: -0.0000

Data Index: 176913 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3521. Min Act: -0.0000

Data Index: 908755 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3491. Min Act: -0.0000

Data Index: 319909 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3261. Min Act: -0.0000

Data Index: 411371 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3147. Min Act: -0.0000

Data Index: 1155045 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3327. Min Act: -0.0000

Data Index: 600027 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3234. Min Act: -0.0000

Data Index: 808897 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3123. Min Act: -0.0000

Data Index: 1327182 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1058694 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3086. Min Act: -0.0000

Data Index: 908191 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1000473 (C4 (Web Text))

Max Activating Token Index: 361