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

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

Neuron 2129 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0483. Min Range: -3.0483

Max Act: 3.0483. Min Act: -0.0000

Data Index: 1212082 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 3.0483. Min Range: -3.0483

Max Act: 2.6209. Min Act: -0.0000

Data Index: 723153 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 3.0483. Min Range: -3.0483

Max Act: 2.4579. Min Act: -0.0000

Data Index: 767232 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 3.0483. Min Range: -3.0483

Max Act: 2.5543. Min Act: -0.0000

Data Index: 582881 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 3.0483. Min Range: -3.0483

Max Act: 2.5440. Min Act: -0.0000

Data Index: 1059919 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 3.0483. Min Range: -3.0483

Max Act: 2.6215. Min Act: -0.0000

Data Index: 723447 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 3.0483. Min Range: -3.0483

Max Act: 2.5826. Min Act: -0.0000

Data Index: 826644 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 3.0483. Min Range: -3.0483

Max Act: 2.4296. Min Act: -0.0000

Data Index: 900570 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 3.0483. Min Range: -3.0483

Max Act: 2.5589. Min Act: -0.0000

Data Index: 131365 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 3.0483. Min Range: -3.0483

Max Act: 2.3921. Min Act: -0.0000

Data Index: 1128775 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 3.0483. Min Range: -3.0483

Max Act: 2.2716. Min Act: -0.0000

Data Index: 763437 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 3.0483. Min Range: -3.0483

Max Act: 2.3789. Min Act: -0.0000

Data Index: 842922 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 3.0483. Min Range: -3.0483

Max Act: 2.2351. Min Act: -0.0000

Data Index: 1148686 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 3.0483. Min Range: -3.0483

Max Act: 2.4552. Min Act: -0.0000

Data Index: 677284 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 3.0483. Min Range: -3.0483

Max Act: 2.4172. Min Act: -0.0000

Data Index: 167636 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 3.0483. Min Range: -3.0483

Max Act: 2.2717. Min Act: -0.0000

Data Index: 545693 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 3.0483. Min Range: -3.0483

Max Act: 2.2578. Min Act: -0.0000

Data Index: 1018439 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 3.0483. Min Range: -3.0483

Max Act: 2.2215. Min Act: -0.0000

Data Index: 81111 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 3.0483. Min Range: -3.0483

Max Act: 2.0948. Min Act: -0.0000

Data Index: 629805 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 3.0483. Min Range: -3.0483

Max Act: 2.2112. Min Act: -0.0000

Data Index: 428997 (C4 (Web Text))

Max Activating Token Index: 746