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

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

Neuron 3875 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: 1.4983. Min Range: -1.4983

Max Act: 1.4983. Min Act: -0.0001

Data Index: 44990 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.4371. Min Act: -0.0001

Data Index: 1165948 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.3945. Min Act: -0.0001

Data Index: 1086069 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.2981. Min Act: -0.0000

Data Index: 1358657 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.1543. Min Act: -0.0001

Data Index: 574958 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.3454. Min Act: -0.0000

Data Index: 815012 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.3475. Min Act: -0.0001

Data Index: 1025380 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.2393. Min Act: -0.0001

Data Index: 1048286 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.1868. Min Act: -0.0001

Data Index: 774826 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.2261. Min Act: -0.0001

Data Index: 1114371 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.2568. Min Act: -0.0001

Data Index: 1356404 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.2076. Min Act: -0.0000

Data Index: 1132352 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.1902. Min Act: -0.0001

Data Index: 1123638 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.1913. Min Act: -0.0000

Data Index: 1330499 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.1602. Min Act: -0.0001

Data Index: 533507 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.0567. Min Act: -0.0001

Data Index: 1105685 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.0831. Min Act: -0.0001

Data Index: 451533 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.1746. Min Act: -0.0001

Data Index: 493590 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.1737. Min Act: -0.0001

Data Index: 25419 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.1240. Min Act: -0.0001

Data Index: 629174 (C4 (Web Text))

Max Activating Token Index: 11