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

Dataset: The Pile

Neuron 4498 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1302. Min Range: -1.1302

Max Act: 1.1302. Min Act: -0.0000

Data Index: 725295 (The Pile)

Max Activating Token Index: 364

Text #1

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.9729. Min Act: -0.0000

Data Index: 323319 (The Pile)

Max Activating Token Index: 584

Text #2

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.8773. Min Act: -0.0000

Data Index: 1035573 (The Pile)

Max Activating Token Index: 156

Text #3

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.8690. Min Act: -0.0000

Data Index: 1189164 (The Pile)

Max Activating Token Index: 441

Text #4

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.8814. Min Act: -0.0000

Data Index: 98452 (The Pile)

Max Activating Token Index: 152

Text #5

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.6657. Min Act: -0.0000

Data Index: 1535388 (The Pile)

Max Activating Token Index: 565

Text #6

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.8994. Min Act: -0.0000

Data Index: 774142 (The Pile)

Max Activating Token Index: 200

Text #7

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.8942. Min Act: -0.0000

Data Index: 1544404 (The Pile)

Max Activating Token Index: 340

Text #8

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.8251. Min Act: -0.0000

Data Index: 809390 (The Pile)

Max Activating Token Index: 211

Text #9

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.7952. Min Act: -0.0000

Data Index: 894039 (The Pile)

Max Activating Token Index: 90

Text #10

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.7931. Min Act: -0.0000

Data Index: 30188 (The Pile)

Max Activating Token Index: 194

Text #11

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.8288. Min Act: -0.0000

Data Index: 998936 (The Pile)

Max Activating Token Index: 206

Text #12

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.8256. Min Act: -0.0000

Data Index: 864445 (The Pile)

Max Activating Token Index: 202

Text #13

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1392448 (The Pile)

Max Activating Token Index: 560

Text #14

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.7163. Min Act: -0.0000

Data Index: 981014 (The Pile)

Max Activating Token Index: 143

Text #15

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.8206. Min Act: -0.0000

Data Index: 1271182 (The Pile)

Max Activating Token Index: 136

Text #16

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.7837. Min Act: -0.0000

Data Index: 932477 (The Pile)

Max Activating Token Index: 603

Text #17

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.7380. Min Act: -0.0000

Data Index: 438663 (The Pile)

Max Activating Token Index: 105

Text #18

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.7164. Min Act: -0.0000

Data Index: 853881 (The Pile)

Max Activating Token Index: 194

Text #19

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.7830. Min Act: -0.0000

Data Index: 1136737 (The Pile)

Max Activating Token Index: 231