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

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

Neuron 523 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.9852. Min Act: -0.0002

Data Index: 1407359 (Python Code)

Max Activating Token Index: 216

Text #1

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.5785. Min Act: -0.0002

Data Index: 1365092 (Python Code)

Max Activating Token Index: 621

Text #2

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.4656. Min Act: -0.0002

Data Index: 1527620 (Python Code)

Max Activating Token Index: 565

Text #3

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.3870. Min Act: -0.0002

Data Index: 1395598 (Python Code)

Max Activating Token Index: 820

Text #4

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.3895. Min Act: -0.0002

Data Index: 1577724 (Python Code)

Max Activating Token Index: 458

Text #5

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.5921. Min Act: -0.0002

Data Index: 1512277 (Python Code)

Max Activating Token Index: 900

Text #6

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.4593. Min Act: -0.0002

Data Index: 1421249 (Python Code)

Max Activating Token Index: 544

Text #7

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.4330. Min Act: -0.0002

Data Index: 1579519 (Python Code)

Max Activating Token Index: 351

Text #8

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.2940. Min Act: -0.0002

Data Index: 1601464 (Python Code)

Max Activating Token Index: 11

Text #9

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.3656. Min Act: -0.0002

Data Index: 1534661 (Python Code)

Max Activating Token Index: 563

Text #10

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.2445. Min Act: -0.0002

Data Index: 1375642 (Python Code)

Max Activating Token Index: 134

Text #11

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.3484. Min Act: -0.0002

Data Index: 1484726 (Python Code)

Max Activating Token Index: 944

Text #12

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.3424. Min Act: -0.0002

Data Index: 1600423 (Python Code)

Max Activating Token Index: 526

Text #13

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.2066. Min Act: -0.0002

Data Index: 1400762 (Python Code)

Max Activating Token Index: 520

Text #14

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.2788. Min Act: -0.0002

Data Index: 1425177 (Python Code)

Max Activating Token Index: 250

Text #15

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.1494. Min Act: -0.0002

Data Index: 1380672 (Python Code)

Max Activating Token Index: 236

Text #16

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.2156. Min Act: -0.0002

Data Index: 1616068 (Python Code)

Max Activating Token Index: 865

Text #17

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.3339. Min Act: -0.0002

Data Index: 1653373 (Python Code)

Max Activating Token Index: 751

Text #18

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.1727. Min Act: -0.0002

Data Index: 1519212 (Python Code)

Max Activating Token Index: 408

Text #19

Max Range: 1.9852. Min Range: -1.9852

Max Act: 1.0199. Min Act: -0.0002

Data Index: 1607439 (Python Code)

Max Activating Token Index: 628