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

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

Neuron 1326 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0118. Min Range: -2.0118

Max Act: 1.9343. Min Act: -0.0000

Data Index: 243874 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 2.0118. Min Range: -2.0118

Max Act: 2.0118. Min Act: -0.0000

Data Index: 8115 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 2.0118. Min Range: -2.0118

Max Act: 1.8926. Min Act: -0.0000

Data Index: 739361 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 2.0118. Min Range: -2.0118

Max Act: 1.8761. Min Act: 0.0001

Data Index: 589684 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 2.0118. Min Range: -2.0118

Max Act: 1.8617. Min Act: -0.0000

Data Index: 975075 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 2.0118. Min Range: -2.0118

Max Act: 1.9357. Min Act: -0.0000

Data Index: 480361 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 2.0118. Min Range: -2.0118

Max Act: 1.7976. Min Act: -0.0000

Data Index: 191719 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 2.0118. Min Range: -2.0118

Max Act: 1.8820. Min Act: -0.0000

Data Index: 104340 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 2.0118. Min Range: -2.0118

Max Act: 1.7419. Min Act: -0.0000

Data Index: 1252672 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 2.0118. Min Range: -2.0118

Max Act: 1.5669. Min Act: -0.0000

Data Index: 832758 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 2.0118. Min Range: -2.0118

Max Act: 1.6482. Min Act: -0.0000

Data Index: 633288 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 2.0118. Min Range: -2.0118

Max Act: 1.5502. Min Act: -0.0000

Data Index: 1032612 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 2.0118. Min Range: -2.0118

Max Act: 1.6287. Min Act: -0.0000

Data Index: 241319 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 2.0118. Min Range: -2.0118

Max Act: 1.6252. Min Act: -0.0000

Data Index: 224445 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 2.0118. Min Range: -2.0118

Max Act: 1.6237. Min Act: -0.0000

Data Index: 768624 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 2.0118. Min Range: -2.0118

Max Act: 1.6209. Min Act: -0.0000

Data Index: 221881 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 2.0118. Min Range: -2.0118

Max Act: 1.5096. Min Act: -0.0000

Data Index: 709976 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 2.0118. Min Range: -2.0118

Max Act: 1.5624. Min Act: -0.0000

Data Index: 255424 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 2.0118. Min Range: -2.0118

Max Act: 1.4687. Min Act: -0.0000

Data Index: 593094 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 2.0118. Min Range: -2.0118

Max Act: 1.5497. Min Act: -0.0000

Data Index: 93722 (C4 (Web Text))

Max Activating Token Index: 90