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

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

Neuron 2706 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.6593. Min Act: -0.0000

Data Index: 165347 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.6208. Min Act: -0.0000

Data Index: 1156408 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1278431 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.6034. Min Act: -0.0000

Data Index: 653616 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5828. Min Act: -0.0000

Data Index: 1005434 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5604. Min Act: -0.0000

Data Index: 288174 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5936. Min Act: -0.0000

Data Index: 30175 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5831. Min Act: -0.0000

Data Index: 65153 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5366. Min Act: -0.0000

Data Index: 902538 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5170. Min Act: -0.0000

Data Index: 347867 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5435. Min Act: -0.0000

Data Index: 1351524 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1248679 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5252. Min Act: -0.0000

Data Index: 86150 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5118. Min Act: -0.0000

Data Index: 685549 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.4908. Min Act: -0.0000

Data Index: 19365 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.4618. Min Act: -0.0000

Data Index: 541819 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5179. Min Act: -0.0000

Data Index: 392834 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5148. Min Act: -0.0000

Data Index: 350006 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5120. Min Act: -0.0000

Data Index: 1164509 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5206. Min Act: -0.0000

Data Index: 1003358 (C4 (Web Text))

Max Activating Token Index: 482