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

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

Neuron 6072 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.5892. Min Act: -0.0002

Data Index: 1295243 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.3798. Min Act: -0.0002

Data Index: 413972 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.3715. Min Act: -0.0002

Data Index: 789274 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.3392. Min Act: -0.0002

Data Index: 930609 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.3020. Min Act: -0.0002

Data Index: 551444 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.3152. Min Act: -0.0002

Data Index: 1303823 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.2826. Min Act: -0.0002

Data Index: 10519 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.2930. Min Act: -0.0002

Data Index: 29892 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.2994. Min Act: -0.0002

Data Index: 799640 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.2909. Min Act: -0.0002

Data Index: 944004 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.2506. Min Act: -0.0002

Data Index: 470196 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.2619. Min Act: -0.0002

Data Index: 951794 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.2461. Min Act: -0.0002

Data Index: 1560434 (Python Code)

Max Activating Token Index: 3

Text #13

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.2505. Min Act: -0.0002

Data Index: 1189573 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.2294. Min Act: -0.0002

Data Index: 120224 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.2368. Min Act: -0.0002

Data Index: 1529498 (Python Code)

Max Activating Token Index: 200

Text #16

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.2474. Min Act: -0.0002

Data Index: 968503 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.2072. Min Act: -0.0002

Data Index: 923496 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.2208. Min Act: -0.0002

Data Index: 387653 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.1897. Min Act: -0.0002

Data Index: 222536 (C4 (Web Text))

Max Activating Token Index: 88