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

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

Neuron 4943 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: 1.8084. Min Range: -1.8084

Max Act: 1.6968. Min Act: -0.0001

Data Index: 1535445 (Python Code)

Max Activating Token Index: 449

Text #1

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.8084. Min Act: -0.0001

Data Index: 1587797 (Python Code)

Max Activating Token Index: 611

Text #2

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.4750. Min Act: -0.0001

Data Index: 395547 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.4027. Min Act: -0.0001

Data Index: 1487289 (Python Code)

Max Activating Token Index: 57

Text #4

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3816. Min Act: -0.0001

Data Index: 1475148 (Python Code)

Max Activating Token Index: 345

Text #5

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.4496. Min Act: -0.0001

Data Index: 1413574 (Python Code)

Max Activating Token Index: 848

Text #6

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3779. Min Act: -0.0001

Data Index: 1548436 (Python Code)

Max Activating Token Index: 96

Text #7

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.6038. Min Act: -0.0001

Data Index: 771139 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2753. Min Act: -0.0001

Data Index: 1406871 (Python Code)

Max Activating Token Index: 547

Text #9

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.4215. Min Act: -0.0001

Data Index: 1620026 (Python Code)

Max Activating Token Index: 78

Text #10

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.4839. Min Act: -0.0001

Data Index: 1489627 (Python Code)

Max Activating Token Index: 750

Text #11

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.4436. Min Act: -0.0001

Data Index: 1526886 (Python Code)

Max Activating Token Index: 841

Text #12

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3257. Min Act: -0.0000

Data Index: 1548631 (Python Code)

Max Activating Token Index: 75

Text #13

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2352. Min Act: -0.0001

Data Index: 1571665 (Python Code)

Max Activating Token Index: 61

Text #14

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3537. Min Act: -0.0000

Data Index: 940243 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2389. Min Act: -0.0001

Data Index: 1585995 (Python Code)

Max Activating Token Index: 137

Text #16

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2568. Min Act: -0.0001

Data Index: 1483119 (Python Code)

Max Activating Token Index: 1011

Text #17

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2587. Min Act: -0.0001

Data Index: 165766 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2455. Min Act: -0.0001

Data Index: 1537620 (Python Code)

Max Activating Token Index: 407

Text #19

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2454. Min Act: -0.0001

Data Index: 1592203 (Python Code)

Max Activating Token Index: 96