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

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

Neuron 3074 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.4686. Min Act: -0.0000

Data Index: 276857 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3763. Min Act: -0.0000

Data Index: 153540 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.3159. Min Act: -0.0000

Data Index: 101605 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.2874. Min Act: 0.0000

Data Index: 48661 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.2863. Min Act: -0.0000

Data Index: 304656 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.2628. Min Act: -0.0000

Data Index: 268847 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.2585. Min Act: -0.0000

Data Index: 998819 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.2843. Min Act: -0.0000

Data Index: 1084824 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.2700. Min Act: -0.0000

Data Index: 256478 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.2540. Min Act: 0.0000

Data Index: 1060547 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.2318. Min Act: -0.0000

Data Index: 875088 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.2472. Min Act: -0.0000

Data Index: 666206 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.2424. Min Act: -0.0000

Data Index: 285298 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.2236. Min Act: 0.0000

Data Index: 533347 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.2398. Min Act: -0.0000

Data Index: 1072956 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.2131. Min Act: -0.0000

Data Index: 519700 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.2178. Min Act: -0.0000

Data Index: 7129 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.2095. Min Act: -0.0000

Data Index: 73786 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.1975. Min Act: -0.0000

Data Index: 45677 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 0.4686. Min Range: -0.4686

Max Act: 0.1989. Min Act: -0.0000

Data Index: 1148621 (C4 (Web Text))

Max Activating Token Index: 73