Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3093 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.7697. Min Act: -0.0001

Data Index: 1410535 (Python Code)

Max Activating Token Index: 325

Text #1

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.5188. Min Act: -0.0001

Data Index: 1410438 (Python Code)

Max Activating Token Index: 55

Text #2

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.4167. Min Act: -0.0001

Data Index: 1361200 (Python Code)

Max Activating Token Index: 47

Text #3

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.4686. Min Act: -0.0001

Data Index: 1508348 (Python Code)

Max Activating Token Index: 720

Text #4

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.4942. Min Act: -0.0001

Data Index: 1636279 (Python Code)

Max Activating Token Index: 98

Text #5

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.3969. Min Act: -0.0001

Data Index: 1418454 (Python Code)

Max Activating Token Index: 472

Text #6

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.3857. Min Act: -0.0001

Data Index: 1434604 (Python Code)

Max Activating Token Index: 911

Text #7

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.4687. Min Act: -0.0001

Data Index: 1650739 (Python Code)

Max Activating Token Index: 530

Text #8

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.3710. Min Act: -0.0001

Data Index: 1422442 (Python Code)

Max Activating Token Index: 374

Text #9

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.3252. Min Act: -0.0001

Data Index: 1469821 (Python Code)

Max Activating Token Index: 752

Text #10

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.1943. Min Act: -0.0000

Data Index: 1364176 (Python Code)

Max Activating Token Index: 782

Text #11

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.0893. Min Act: -0.0001

Data Index: 1574572 (Python Code)

Max Activating Token Index: 604

Text #12

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.3312. Min Act: -0.0001

Data Index: 1419835 (Python Code)

Max Activating Token Index: 250

Text #13

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.3295. Min Act: -0.0001

Data Index: 1506001 (Python Code)

Max Activating Token Index: 185

Text #14

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.2158. Min Act: -0.0001

Data Index: 1368977 (Python Code)

Max Activating Token Index: 519

Text #15

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.2649. Min Act: -0.0001

Data Index: 1494487 (Python Code)

Max Activating Token Index: 772

Text #16

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.2586. Min Act: -0.0001

Data Index: 1425440 (Python Code)

Max Activating Token Index: 912

Text #17

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.3310. Min Act: -0.0000

Data Index: 1398433 (Python Code)

Max Activating Token Index: 98

Text #18

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.3739. Min Act: -0.0001

Data Index: 1629919 (Python Code)

Max Activating Token Index: 87

Text #19

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.2466. Min Act: -0.0000

Data Index: 1476368 (Python Code)

Max Activating Token Index: 70