Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1608 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.6607. Min Range: -1.6607

Max Act: 1.5186. Min Act: -0.0001

Data Index: 963006 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 1.6607. Min Range: -1.6607

Max Act: 1.6372. Min Act: -0.0001

Data Index: 247169 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 1.6607. Min Range: -1.6607

Max Act: 1.6307. Min Act: -0.0001

Data Index: 1346615 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 1.6607. Min Range: -1.6607

Max Act: 1.4896. Min Act: -0.0001

Data Index: 222005 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 1.6607. Min Range: -1.6607

Max Act: 1.5337. Min Act: -0.0001

Data Index: 655369 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 1.6607. Min Range: -1.6607

Max Act: 1.6607. Min Act: -0.0001

Data Index: 469718 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 1.6607. Min Range: -1.6607

Max Act: 1.5208. Min Act: -0.0001

Data Index: 718765 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 1.6607. Min Range: -1.6607

Max Act: 1.5400. Min Act: -0.0001

Data Index: 694845 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 1.6607. Min Range: -1.6607

Max Act: 1.4348. Min Act: -0.0001

Data Index: 436750 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 1.6607. Min Range: -1.6607

Max Act: 1.4020. Min Act: -0.0001

Data Index: 310911 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 1.6607. Min Range: -1.6607

Max Act: 1.6173. Min Act: -0.0001

Data Index: 296128 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 1.6607. Min Range: -1.6607

Max Act: 1.4233. Min Act: -0.0001

Data Index: 1092023 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 1.6607. Min Range: -1.6607

Max Act: 1.2654. Min Act: -0.0001

Data Index: 1147473 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 1.6607. Min Range: -1.6607

Max Act: 1.4527. Min Act: -0.0001

Data Index: 1211200 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 1.6607. Min Range: -1.6607

Max Act: 1.3734. Min Act: -0.0001

Data Index: 537243 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 1.6607. Min Range: -1.6607

Max Act: 1.3957. Min Act: -0.0001

Data Index: 925172 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 1.6607. Min Range: -1.6607

Max Act: 1.4198. Min Act: -0.0001

Data Index: 672233 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 1.6607. Min Range: -1.6607

Max Act: 1.3772. Min Act: -0.0001

Data Index: 584500 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 1.6607. Min Range: -1.6607

Max Act: 1.3551. Min Act: -0.0001

Data Index: 34800 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 1.6607. Min Range: -1.6607

Max Act: 1.3904. Min Act: -0.0001

Data Index: 834681 (C4 (Web Text))

Max Activating Token Index: 663