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

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

Neuron 1490 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.4299. Min Range: -8.4299

Max Act: 8.4299. Min Act: -0.0000

Data Index: 727585 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 8.4299. Min Range: -8.4299

Max Act: 8.2882. Min Act: -0.0000

Data Index: 492071 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 8.4299. Min Range: -8.4299

Max Act: 3.3044. Min Act: -0.0000

Data Index: 272849 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 8.4299. Min Range: -8.4299

Max Act: 3.2933. Min Act: -0.0000

Data Index: 882945 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 8.4299. Min Range: -8.4299

Max Act: 3.1472. Min Act: -0.0000

Data Index: 980400 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 8.4299. Min Range: -8.4299

Max Act: 3.1034. Min Act: -0.0000

Data Index: 327293 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 8.4299. Min Range: -8.4299

Max Act: 2.9180. Min Act: -0.0000

Data Index: 538531 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 8.4299. Min Range: -8.4299

Max Act: 2.9433. Min Act: -0.0000

Data Index: 31084 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 8.4299. Min Range: -8.4299

Max Act: 2.6768. Min Act: -0.0000

Data Index: 1164950 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 8.4299. Min Range: -8.4299

Max Act: 2.6141. Min Act: -0.0000

Data Index: 232501 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 8.4299. Min Range: -8.4299

Max Act: 2.7247. Min Act: -0.0000

Data Index: 1222476 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 8.4299. Min Range: -8.4299

Max Act: 2.5727. Min Act: -0.0000

Data Index: 342162 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 8.4299. Min Range: -8.4299

Max Act: 2.5804. Min Act: -0.0000

Data Index: 1282366 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 8.4299. Min Range: -8.4299

Max Act: 2.5899. Min Act: -0.0000

Data Index: 1046552 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 8.4299. Min Range: -8.4299

Max Act: 2.5870. Min Act: -0.0000

Data Index: 725055 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 8.4299. Min Range: -8.4299

Max Act: 2.6456. Min Act: -0.0000

Data Index: 838085 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 8.4299. Min Range: -8.4299

Max Act: 2.4952. Min Act: -0.0000

Data Index: 1142107 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 8.4299. Min Range: -8.4299

Max Act: 2.4831. Min Act: -0.0000

Data Index: 159022 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 8.4299. Min Range: -8.4299

Max Act: 2.3288. Min Act: -0.0000

Data Index: 203154 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 8.4299. Min Range: -8.4299

Max Act: 2.4136. Min Act: -0.0000

Data Index: 67606 (C4 (Web Text))

Max Activating Token Index: 149