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

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

Neuron 4511 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6933. Min Range: -1.6933

Max Act: 1.6933. Min Act: -0.0000

Data Index: 1371367 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 1.6933. Min Range: -1.6933

Max Act: 1.6903. Min Act: -0.0001

Data Index: 1567341 (Python Code)

Max Activating Token Index: 186

Text #2

Max Range: 1.6933. Min Range: -1.6933

Max Act: 1.5772. Min Act: -0.0000

Data Index: 1510285 (Python Code)

Max Activating Token Index: 30

Text #3

Max Range: 1.6933. Min Range: -1.6933

Max Act: 1.5683. Min Act: -0.0001

Data Index: 1599235 (Python Code)

Max Activating Token Index: 68

Text #4

Max Range: 1.6933. Min Range: -1.6933

Max Act: 1.4305. Min Act: -0.0000

Data Index: 1393885 (Python Code)

Max Activating Token Index: 147

Text #5

Max Range: 1.6933. Min Range: -1.6933

Max Act: 1.3580. Min Act: -0.0001

Data Index: 1434794 (Python Code)

Max Activating Token Index: 875

Text #6

Max Range: 1.6933. Min Range: -1.6933

Max Act: 1.3761. Min Act: -0.0001

Data Index: 1625268 (Python Code)

Max Activating Token Index: 55

Text #7

Max Range: 1.6933. Min Range: -1.6933

Max Act: 1.3567. Min Act: -0.0001

Data Index: 1552064 (Python Code)

Max Activating Token Index: 143

Text #8

Max Range: 1.6933. Min Range: -1.6933

Max Act: 1.3532. Min Act: -0.0000

Data Index: 1495897 (Python Code)

Max Activating Token Index: 31

Text #9

Max Range: 1.6933. Min Range: -1.6933

Max Act: 1.2358. Min Act: -0.0000

Data Index: 1587843 (Python Code)

Max Activating Token Index: 124

Text #10

Max Range: 1.6933. Min Range: -1.6933

Max Act: 1.3073. Min Act: -0.0000

Data Index: 1442325 (Python Code)

Max Activating Token Index: 382

Text #11

Max Range: 1.6933. Min Range: -1.6933

Max Act: 1.4250. Min Act: -0.0000

Data Index: 1408262 (Python Code)

Max Activating Token Index: 234

Text #12

Max Range: 1.6933. Min Range: -1.6933

Max Act: 1.3508. Min Act: -0.0001

Data Index: 1554402 (Python Code)

Max Activating Token Index: 892

Text #13

Max Range: 1.6933. Min Range: -1.6933

Max Act: 1.3032. Min Act: -0.0001

Data Index: 1374209 (Python Code)

Max Activating Token Index: 8

Text #14

Max Range: 1.6933. Min Range: -1.6933

Max Act: 1.3301. Min Act: -0.0000

Data Index: 1473818 (Python Code)

Max Activating Token Index: 60

Text #15

Max Range: 1.6933. Min Range: -1.6933

Max Act: 1.2578. Min Act: -0.0000

Data Index: 1415946 (Python Code)

Max Activating Token Index: 772

Text #16

Max Range: 1.6933. Min Range: -1.6933

Max Act: 1.2797. Min Act: -0.0001

Data Index: 1511203 (Python Code)

Max Activating Token Index: 87

Text #17

Max Range: 1.6933. Min Range: -1.6933

Max Act: 1.2738. Min Act: -0.0001

Data Index: 1496787 (Python Code)

Max Activating Token Index: 14

Text #18

Max Range: 1.6933. Min Range: -1.6933

Max Act: 1.2985. Min Act: -0.0001

Data Index: 1444999 (Python Code)

Max Activating Token Index: 26

Text #19

Max Range: 1.6933. Min Range: -1.6933

Max Act: 1.3359. Min Act: -0.0001

Data Index: 1620441 (Python Code)

Max Activating Token Index: 302