Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3163 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.4293. Min Act: -0.0000

Data Index: 1176917 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3933. Min Act: -0.0000

Data Index: 893889 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3950. Min Act: -0.0000

Data Index: 529490 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3374. Min Act: -0.0000

Data Index: 457061 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3278. Min Act: -0.0000

Data Index: 753869 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3072. Min Act: -0.0000

Data Index: 693279 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3115. Min Act: -0.0000

Data Index: 539739 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.2998. Min Act: -0.0000

Data Index: 508837 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.3140. Min Act: -0.0000

Data Index: 3858 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.2944. Min Act: -0.0000

Data Index: 410519 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.2953. Min Act: -0.0000

Data Index: 686915 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.2751. Min Act: 0.0000

Data Index: 1401740 (Python Code)

Max Activating Token Index: 328

Text #12

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.2877. Min Act: -0.0000

Data Index: 153060 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.2741. Min Act: -0.0000

Data Index: 1184781 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.2681. Min Act: -0.0000

Data Index: 804056 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.2747. Min Act: -0.0000

Data Index: 589950 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.2795. Min Act: -0.0000

Data Index: 141729 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.2655. Min Act: -0.0000

Data Index: 655622 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.2566. Min Act: -0.0000

Data Index: 1092236 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.4293. Min Range: -0.4293

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1610716 (Python Code)

Max Activating Token Index: 655