Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2737 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.9599. Min Act: -0.0001

Data Index: 1621335 (Python Code)

Max Activating Token Index: 580

Text #1

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.9134. Min Act: -0.0001

Data Index: 1646942 (Python Code)

Max Activating Token Index: 404

Text #2

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.9653. Min Act: -0.0001

Data Index: 1509379 (Python Code)

Max Activating Token Index: 545

Text #3

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.9494. Min Act: -0.0001

Data Index: 1452189 (Python Code)

Max Activating Token Index: 84

Text #4

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8927. Min Act: -0.0001

Data Index: 1477413 (Python Code)

Max Activating Token Index: 813

Text #5

Max Range: 1.0346. Min Range: -1.0346

Max Act: 1.0346. Min Act: -0.0001

Data Index: 1549066 (Python Code)

Max Activating Token Index: 784

Text #6

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8613. Min Act: -0.0001

Data Index: 1393248 (Python Code)

Max Activating Token Index: 701

Text #7

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.9003. Min Act: -0.0001

Data Index: 1456667 (Python Code)

Max Activating Token Index: 288

Text #8

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8942. Min Act: -0.0001

Data Index: 1508238 (Python Code)

Max Activating Token Index: 676

Text #9

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8623. Min Act: -0.0001

Data Index: 1463094 (Python Code)

Max Activating Token Index: 266

Text #10

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8651. Min Act: -0.0001

Data Index: 1366201 (Python Code)

Max Activating Token Index: 272

Text #11

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8851. Min Act: -0.0001

Data Index: 1501533 (Python Code)

Max Activating Token Index: 790

Text #12

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8138. Min Act: -0.0001

Data Index: 1459961 (Python Code)

Max Activating Token Index: 287

Text #13

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.9302. Min Act: -0.0001

Data Index: 1510089 (Python Code)

Max Activating Token Index: 933

Text #14

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.9020. Min Act: -0.0001

Data Index: 1464420 (Python Code)

Max Activating Token Index: 320

Text #15

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8660. Min Act: -0.0001

Data Index: 1407508 (Python Code)

Max Activating Token Index: 341

Text #16

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.7619. Min Act: -0.0001

Data Index: 1562029 (Python Code)

Max Activating Token Index: 940

Text #17

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8106. Min Act: -0.0001

Data Index: 1470953 (Python Code)

Max Activating Token Index: 926

Text #18

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8390. Min Act: -0.0001

Data Index: 1571108 (Python Code)

Max Activating Token Index: 901

Text #19

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8679. Min Act: -0.0001

Data Index: 1525536 (Python Code)

Max Activating Token Index: 220