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

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

Neuron 4763 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2728. Min Range: -1.2728

Max Act: 1.2728. Min Act: 0.0000

Data Index: 1157532 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 1.2728. Min Range: -1.2728

Max Act: 1.2321. Min Act: -0.0000

Data Index: 793708 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 1.2728. Min Range: -1.2728

Max Act: 1.0488. Min Act: 0.0000

Data Index: 50912 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 1.2728. Min Range: -1.2728

Max Act: 1.0062. Min Act: -0.0000

Data Index: 778663 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 1.2728. Min Range: -1.2728

Max Act: 0.8975. Min Act: 0.0000

Data Index: 707649 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 1.2728. Min Range: -1.2728

Max Act: 0.9373. Min Act: 0.0002

Data Index: 595732 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 1.2728. Min Range: -1.2728

Max Act: 0.9364. Min Act: -0.0000

Data Index: 1168731 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 1.2728. Min Range: -1.2728

Max Act: 0.9309. Min Act: -0.0000

Data Index: 423882 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 1.2728. Min Range: -1.2728

Max Act: 0.9290. Min Act: 0.0000

Data Index: 1131830 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 1.2728. Min Range: -1.2728

Max Act: 0.9399. Min Act: -0.0000

Data Index: 967915 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 1.2728. Min Range: -1.2728

Max Act: 0.9232. Min Act: -0.0000

Data Index: 976282 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 1.2728. Min Range: -1.2728

Max Act: 0.9433. Min Act: -0.0000

Data Index: 416933 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 1.2728. Min Range: -1.2728

Max Act: 0.9195. Min Act: 0.0002

Data Index: 1144383 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 1.2728. Min Range: -1.2728

Max Act: 0.8819. Min Act: 0.0000

Data Index: 354134 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 1.2728. Min Range: -1.2728

Max Act: 0.8796. Min Act: -0.0000

Data Index: 813589 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 1.2728. Min Range: -1.2728

Max Act: 0.8700. Min Act: -0.0000

Data Index: 43027 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 1.2728. Min Range: -1.2728

Max Act: 0.8879. Min Act: 0.0002

Data Index: 1265021 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 1.2728. Min Range: -1.2728

Max Act: 0.8964. Min Act: 0.0001

Data Index: 511732 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 1.2728. Min Range: -1.2728

Max Act: 0.9078. Min Act: -0.0000

Data Index: 1243933 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 1.2728. Min Range: -1.2728

Max Act: 0.9120. Min Act: -0.0000

Data Index: 1035489 (C4 (Web Text))

Max Activating Token Index: 928