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

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

Neuron 1378 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5487. Min Act: -0.0000

Data Index: 33272 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5705. Min Act: -0.0000

Data Index: 845333 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5172. Min Act: -0.0000

Data Index: 206527 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1321735 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1157994 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.3933. Min Act: -0.0000

Data Index: 370860 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.3772. Min Act: -0.0000

Data Index: 972039 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.3483. Min Act: -0.0000

Data Index: 845746 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.3515. Min Act: -0.0000

Data Index: 1026038 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.3236. Min Act: -0.0000

Data Index: 454515 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.3625. Min Act: -0.0000

Data Index: 413624 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1187193 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.3370. Min Act: -0.0000

Data Index: 832318 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.2897. Min Act: -0.0000

Data Index: 1343197 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.3039. Min Act: -0.0000

Data Index: 1068383 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.2636. Min Act: -0.0000

Data Index: 650308 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.2731. Min Act: -0.0000

Data Index: 1068259 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.2262. Min Act: -0.0000

Data Index: 1256599 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1015953 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.2440. Min Act: -0.0000

Data Index: 201424 (C4 (Web Text))

Max Activating Token Index: 173