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

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

Neuron 4646 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: 1.6974. Min Range: -1.6974

Max Act: 1.6974. Min Act: -0.0000

Data Index: 1594359 (Python Code)

Max Activating Token Index: 590

Text #1

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.4605. Min Act: -0.0000

Data Index: 1625265 (Python Code)

Max Activating Token Index: 920

Text #2

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.3563. Min Act: 0.0001

Data Index: 1369370 (Python Code)

Max Activating Token Index: 45

Text #3

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.3848. Min Act: 0.0001

Data Index: 1535819 (Python Code)

Max Activating Token Index: 412

Text #4

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.3972. Min Act: 0.0000

Data Index: 1481770 (Python Code)

Max Activating Token Index: 77

Text #5

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.3259. Min Act: 0.0001

Data Index: 1567766 (Python Code)

Max Activating Token Index: 52

Text #6

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.3255. Min Act: 0.0000

Data Index: 1366547 (Python Code)

Max Activating Token Index: 624

Text #7

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.3643. Min Act: 0.0000

Data Index: 1504657 (Python Code)

Max Activating Token Index: 121

Text #8

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.3364. Min Act: -0.0000

Data Index: 1590888 (Python Code)

Max Activating Token Index: 615

Text #9

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.2467. Min Act: 0.0000

Data Index: 1456818 (Python Code)

Max Activating Token Index: 347

Text #10

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.3181. Min Act: 0.0000

Data Index: 1438184 (Python Code)

Max Activating Token Index: 713

Text #11

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.3053. Min Act: 0.0001

Data Index: 1557371 (Python Code)

Max Activating Token Index: 781

Text #12

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.2742. Min Act: -0.0000

Data Index: 1393927 (Python Code)

Max Activating Token Index: 133

Text #13

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.2617. Min Act: -0.0000

Data Index: 222713 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.2505. Min Act: -0.0000

Data Index: 1390617 (Python Code)

Max Activating Token Index: 811

Text #15

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.1427. Min Act: 0.0001

Data Index: 1387239 (Python Code)

Max Activating Token Index: 945

Text #16

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.1466. Min Act: -0.0000

Data Index: 1446211 (Python Code)

Max Activating Token Index: 445

Text #17

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.1593. Min Act: -0.0000

Data Index: 1559852 (Python Code)

Max Activating Token Index: 194

Text #18

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.1819. Min Act: -0.0000

Data Index: 1570396 (Python Code)

Max Activating Token Index: 487

Text #19

Max Range: 1.6974. Min Range: -1.6974

Max Act: 1.2130. Min Act: -0.0000

Data Index: 1093128 (C4 (Web Text))

Max Activating Token Index: 834