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

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

Neuron 5905 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1939. Min Act: -0.0000

Data Index: 671832 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1808. Min Act: -0.0000

Data Index: 104557 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1719. Min Act: -0.0000

Data Index: 152053 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1698. Min Act: -0.0000

Data Index: 97656 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1698. Min Act: -0.0000

Data Index: 187180 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1561. Min Act: -0.0000

Data Index: 167726 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1388. Min Act: -0.0000

Data Index: 875728 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1488. Min Act: -0.0000

Data Index: 1216859 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1477. Min Act: -0.0000

Data Index: 233546 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1477. Min Act: -0.0000

Data Index: 1283176 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1505. Min Act: -0.0000

Data Index: 591917 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1430. Min Act: -0.0000

Data Index: 744964 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1467. Min Act: -0.0000

Data Index: 191219 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1425. Min Act: -0.0000

Data Index: 905386 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1501. Min Act: -0.0000

Data Index: 951137 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1399. Min Act: -0.0000

Data Index: 1051425 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1414. Min Act: -0.0000

Data Index: 945124 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1312. Min Act: -0.0000

Data Index: 911172 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1384. Min Act: -0.0000

Data Index: 947053 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1350. Min Act: -0.0000

Data Index: 477715 (C4 (Web Text))

Max Activating Token Index: 430