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

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

Neuron 1148 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.4428. Min Act: -0.0001

Data Index: 833199 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.3951. Min Act: -0.0001

Data Index: 158479 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.4050. Min Act: -0.0001

Data Index: 528395 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.3341. Min Act: -0.0001

Data Index: 401662 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.3402. Min Act: -0.0001

Data Index: 592129 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.3188. Min Act: -0.0001

Data Index: 1112035 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.3455. Min Act: -0.0000

Data Index: 264300 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.3357. Min Act: -0.0000

Data Index: 950234 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.2925. Min Act: -0.0000

Data Index: 1055771 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.2639. Min Act: -0.0001

Data Index: 360473 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.2467. Min Act: -0.0000

Data Index: 307442 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.2321. Min Act: -0.0000

Data Index: 1108849 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.2262. Min Act: -0.0000

Data Index: 351109 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.2047. Min Act: -0.0001

Data Index: 640902 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.2303. Min Act: -0.0000

Data Index: 541193 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.2342. Min Act: -0.0001

Data Index: 577820 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.2265. Min Act: -0.0001

Data Index: 1138312 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.2676. Min Act: -0.0001

Data Index: 891846 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.2208. Min Act: -0.0001

Data Index: 1098257 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.2114. Min Act: -0.0001

Data Index: 496636 (C4 (Web Text))

Max Activating Token Index: 838