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

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

Neuron 795 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5405. Min Range: -2.5405

Max Act: 2.5405. Min Act: -0.0000

Data Index: 1161025 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 2.5405. Min Range: -2.5405

Max Act: 2.0021. Min Act: -0.0000

Data Index: 41066 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.5831. Min Act: -0.0000

Data Index: 384523 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.2140. Min Act: -0.0000

Data Index: 340373 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.3548. Min Act: -0.0000

Data Index: 462752 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.2567. Min Act: -0.0000

Data Index: 1064723 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.1810. Min Act: -0.0000

Data Index: 1097370 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.2389. Min Act: -0.0000

Data Index: 932662 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.3134. Min Act: -0.0000

Data Index: 1003699 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.2786. Min Act: -0.0000

Data Index: 210660 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.1224. Min Act: -0.0000

Data Index: 1344765 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.2334. Min Act: -0.0000

Data Index: 176156 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.0295. Min Act: -0.0000

Data Index: 311808 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.1500. Min Act: -0.0000

Data Index: 550575 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.1311. Min Act: -0.0000

Data Index: 858706 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.1975. Min Act: -0.0000

Data Index: 578726 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.0588. Min Act: -0.0000

Data Index: 1179990 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.1930. Min Act: -0.0000

Data Index: 616959 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.1004. Min Act: -0.0000

Data Index: 787691 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.1040. Min Act: -0.0000

Data Index: 410307 (C4 (Web Text))

Max Activating Token Index: 480