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

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

Neuron 4354 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.1154. Min Range: -11.1154

Max Act: 11.1154. Min Act: -0.0000

Data Index: 149238 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 11.1154. Min Range: -11.1154

Max Act: 10.8819. Min Act: -0.0000

Data Index: 1088462 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 11.1154. Min Range: -11.1154

Max Act: 10.5774. Min Act: -0.0000

Data Index: 1239580 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 11.1154. Min Range: -11.1154

Max Act: 10.3378. Min Act: -0.0000

Data Index: 156106 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 11.1154. Min Range: -11.1154

Max Act: 10.4161. Min Act: -0.0000

Data Index: 570125 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 11.1154. Min Range: -11.1154

Max Act: 10.1048. Min Act: -0.0000

Data Index: 602273 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 11.1154. Min Range: -11.1154

Max Act: 10.0566. Min Act: -0.0000

Data Index: 554727 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 11.1154. Min Range: -11.1154

Max Act: 10.1055. Min Act: -0.0000

Data Index: 1098730 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 11.1154. Min Range: -11.1154

Max Act: 9.9100. Min Act: -0.0000

Data Index: 1274574 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 11.1154. Min Range: -11.1154

Max Act: 9.9482. Min Act: -0.0000

Data Index: 77159 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 11.1154. Min Range: -11.1154

Max Act: 9.7677. Min Act: -0.0000

Data Index: 1153004 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 11.1154. Min Range: -11.1154

Max Act: 9.6305. Min Act: -0.0000

Data Index: 1090681 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 11.1154. Min Range: -11.1154

Max Act: 9.5939. Min Act: -0.0000

Data Index: 733848 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 11.1154. Min Range: -11.1154

Max Act: 9.5637. Min Act: -0.0000

Data Index: 525040 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 11.1154. Min Range: -11.1154

Max Act: 9.3841. Min Act: -0.0000

Data Index: 222559 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 11.1154. Min Range: -11.1154

Max Act: 9.6082. Min Act: -0.0000

Data Index: 281887 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 11.1154. Min Range: -11.1154

Max Act: 9.6962. Min Act: -0.0000

Data Index: 45227 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 11.1154. Min Range: -11.1154

Max Act: 9.4668. Min Act: -0.0000

Data Index: 652815 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 11.1154. Min Range: -11.1154

Max Act: 9.6061. Min Act: -0.0000

Data Index: 318379 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 11.1154. Min Range: -11.1154

Max Act: 9.2620. Min Act: -0.0000

Data Index: 1042910 (C4 (Web Text))

Max Activating Token Index: 252