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

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

Neuron 5218 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7275. Min Range: -2.7275

Max Act: 2.7275. Min Act: 0.0000

Data Index: 1597361 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 2.7275. Min Range: -2.7275

Max Act: 2.7150. Min Act: 0.0000

Data Index: 1394614 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 2.7275. Min Range: -2.7275

Max Act: 2.6491. Min Act: -0.0000

Data Index: 1465831 (Python Code)

Max Activating Token Index: 65

Text #3

Max Range: 2.7275. Min Range: -2.7275

Max Act: 2.1040. Min Act: 0.0000

Data Index: 1395624 (Python Code)

Max Activating Token Index: 386

Text #4

Max Range: 2.7275. Min Range: -2.7275

Max Act: 1.9491. Min Act: -0.0000

Data Index: 1630915 (Python Code)

Max Activating Token Index: 274

Text #5

Max Range: 2.7275. Min Range: -2.7275

Max Act: 2.0976. Min Act: 0.0000

Data Index: 1382521 (Python Code)

Max Activating Token Index: 148

Text #6

Max Range: 2.7275. Min Range: -2.7275

Max Act: 1.8145. Min Act: 0.0000

Data Index: 1593188 (Python Code)

Max Activating Token Index: 287

Text #7

Max Range: 2.7275. Min Range: -2.7275

Max Act: 1.8980. Min Act: 0.0000

Data Index: 1484957 (Python Code)

Max Activating Token Index: 346

Text #8

Max Range: 2.7275. Min Range: -2.7275

Max Act: 1.8475. Min Act: -0.0000

Data Index: 1388455 (Python Code)

Max Activating Token Index: 132

Text #9

Max Range: 2.7275. Min Range: -2.7275

Max Act: 1.8333. Min Act: 0.0000

Data Index: 1472195 (Python Code)

Max Activating Token Index: 500

Text #10

Max Range: 2.7275. Min Range: -2.7275

Max Act: 1.8258. Min Act: -0.0000

Data Index: 1609933 (Python Code)

Max Activating Token Index: 579

Text #11

Max Range: 2.7275. Min Range: -2.7275

Max Act: 1.8332. Min Act: 0.0000

Data Index: 1614910 (Python Code)

Max Activating Token Index: 13

Text #12

Max Range: 2.7275. Min Range: -2.7275

Max Act: 1.7108. Min Act: 0.0000

Data Index: 1475098 (Python Code)

Max Activating Token Index: 891

Text #13

Max Range: 2.7275. Min Range: -2.7275

Max Act: 1.7917. Min Act: -0.0000

Data Index: 1325883 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 2.7275. Min Range: -2.7275

Max Act: 1.5530. Min Act: -0.0000

Data Index: 1533455 (Python Code)

Max Activating Token Index: 334

Text #15

Max Range: 2.7275. Min Range: -2.7275

Max Act: 1.6970. Min Act: -0.0000

Data Index: 1569338 (Python Code)

Max Activating Token Index: 209

Text #16

Max Range: 2.7275. Min Range: -2.7275

Max Act: 1.6933. Min Act: -0.0000

Data Index: 128141 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 2.7275. Min Range: -2.7275

Max Act: 1.8424. Min Act: 0.0000

Data Index: 1377807 (Python Code)

Max Activating Token Index: 732

Text #18

Max Range: 2.7275. Min Range: -2.7275

Max Act: 1.7491. Min Act: -0.0000

Data Index: 1506453 (Python Code)

Max Activating Token Index: 657

Text #19

Max Range: 2.7275. Min Range: -2.7275

Max Act: 1.6466. Min Act: -0.0000

Data Index: 1443294 (Python Code)

Max Activating Token Index: 561