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

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

Neuron 4729 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: 0.4409. Min Range: -0.4409

Max Act: 0.4409. Min Act: -0.0001

Data Index: 227521 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3975. Min Act: -0.0001

Data Index: 410065 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3942. Min Act: -0.0001

Data Index: 938332 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3865. Min Act: -0.0001

Data Index: 1087252 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3964. Min Act: -0.0001

Data Index: 433379 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3866. Min Act: -0.0001

Data Index: 1056945 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.4059. Min Act: -0.0001

Data Index: 1317334 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3890. Min Act: -0.0001

Data Index: 100740 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3797. Min Act: -0.0001

Data Index: 837938 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3721. Min Act: -0.0001

Data Index: 114147 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3478. Min Act: -0.0001

Data Index: 1283059 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3727. Min Act: -0.0001

Data Index: 441050 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3681. Min Act: -0.0001

Data Index: 253781 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3564. Min Act: -0.0001

Data Index: 223498 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3471. Min Act: -0.0001

Data Index: 532540 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3684. Min Act: -0.0001

Data Index: 675340 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3625. Min Act: -0.0001

Data Index: 538299 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3421. Min Act: -0.0001

Data Index: 1299097 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3532. Min Act: -0.0001

Data Index: 1181341 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3626. Min Act: -0.0001

Data Index: 1161647 (C4 (Web Text))

Max Activating Token Index: 972