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

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

Neuron 5777 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6321. Min Range: -4.6321

Max Act: 4.6321. Min Act: -0.0000

Data Index: 1637981 (Python Code)

Max Activating Token Index: 857

Text #1

Max Range: 4.6321. Min Range: -4.6321

Max Act: 3.0605. Min Act: -0.0000

Data Index: 1441153 (Python Code)

Max Activating Token Index: 254

Text #2

Max Range: 4.6321. Min Range: -4.6321

Max Act: 3.1255. Min Act: -0.0000

Data Index: 583809 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 4.6321. Min Range: -4.6321

Max Act: 3.0837. Min Act: -0.0000

Data Index: 1438835 (Python Code)

Max Activating Token Index: 64

Text #4

Max Range: 4.6321. Min Range: -4.6321

Max Act: 2.9847. Min Act: -0.0000

Data Index: 1415122 (Python Code)

Max Activating Token Index: 872

Text #5

Max Range: 4.6321. Min Range: -4.6321

Max Act: 2.9863. Min Act: -0.0000

Data Index: 145508 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 4.6321. Min Range: -4.6321

Max Act: 2.8411. Min Act: -0.0000

Data Index: 1393507 (Python Code)

Max Activating Token Index: 375

Text #7

Max Range: 4.6321. Min Range: -4.6321

Max Act: 2.8075. Min Act: -0.0000

Data Index: 1381669 (Python Code)

Max Activating Token Index: 510

Text #8

Max Range: 4.6321. Min Range: -4.6321

Max Act: 2.6682. Min Act: -0.0000

Data Index: 1445906 (Python Code)

Max Activating Token Index: 31

Text #9

Max Range: 4.6321. Min Range: -4.6321

Max Act: 2.6354. Min Act: -0.0000

Data Index: 1620963 (Python Code)

Max Activating Token Index: 476

Text #10

Max Range: 4.6321. Min Range: -4.6321

Max Act: 2.5742. Min Act: -0.0000

Data Index: 1615709 (Python Code)

Max Activating Token Index: 979

Text #11

Max Range: 4.6321. Min Range: -4.6321

Max Act: 2.7028. Min Act: -0.0000

Data Index: 1485948 (Python Code)

Max Activating Token Index: 152

Text #12

Max Range: 4.6321. Min Range: -4.6321

Max Act: 2.5394. Min Act: -0.0000

Data Index: 1071685 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 4.6321. Min Range: -4.6321

Max Act: 2.5429. Min Act: -0.0000

Data Index: 1467040 (Python Code)

Max Activating Token Index: 719

Text #14

Max Range: 4.6321. Min Range: -4.6321

Max Act: 2.3083. Min Act: -0.0000

Data Index: 1487905 (Python Code)

Max Activating Token Index: 687

Text #15

Max Range: 4.6321. Min Range: -4.6321

Max Act: 2.3276. Min Act: -0.0000

Data Index: 78463 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 4.6321. Min Range: -4.6321

Max Act: 2.3070. Min Act: -0.0000

Data Index: 1635025 (Python Code)

Max Activating Token Index: 383

Text #17

Max Range: 4.6321. Min Range: -4.6321

Max Act: 2.4392. Min Act: -0.0000

Data Index: 1525953 (Python Code)

Max Activating Token Index: 135

Text #18

Max Range: 4.6321. Min Range: -4.6321

Max Act: 2.4172. Min Act: -0.0000

Data Index: 1459096 (Python Code)

Max Activating Token Index: 53

Text #19

Max Range: 4.6321. Min Range: -4.6321

Max Act: 2.1870. Min Act: -0.0000

Data Index: 1379357 (Python Code)

Max Activating Token Index: 269