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

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

Neuron 1601 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4337. Min Range: -2.4337

Max Act: 2.4337. Min Act: -0.0000

Data Index: 405112 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 2.4337. Min Range: -2.4337

Max Act: 2.2993. Min Act: -0.0000

Data Index: 1049262 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 2.4337. Min Range: -2.4337

Max Act: 2.3914. Min Act: -0.0000

Data Index: 367306 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 2.4337. Min Range: -2.4337

Max Act: 1.8557. Min Act: -0.0000

Data Index: 478019 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 2.4337. Min Range: -2.4337

Max Act: 1.8613. Min Act: -0.0000

Data Index: 994292 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 2.4337. Min Range: -2.4337

Max Act: 1.9605. Min Act: -0.0000

Data Index: 720796 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 2.4337. Min Range: -2.4337

Max Act: 1.7490. Min Act: -0.0000

Data Index: 828682 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 2.4337. Min Range: -2.4337

Max Act: 1.6211. Min Act: -0.0000

Data Index: 279900 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 2.4337. Min Range: -2.4337

Max Act: 1.3757. Min Act: -0.0000

Data Index: 374987 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 2.4337. Min Range: -2.4337

Max Act: 1.4690. Min Act: -0.0000

Data Index: 1315739 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 2.4337. Min Range: -2.4337

Max Act: 1.3824. Min Act: -0.0000

Data Index: 38188 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 2.4337. Min Range: -2.4337

Max Act: 1.4132. Min Act: -0.0000

Data Index: 292934 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 2.4337. Min Range: -2.4337

Max Act: 1.4293. Min Act: -0.0000

Data Index: 915734 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 2.4337. Min Range: -2.4337

Max Act: 1.2694. Min Act: -0.0000

Data Index: 485540 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 2.4337. Min Range: -2.4337

Max Act: 1.3522. Min Act: -0.0000

Data Index: 1289241 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 2.4337. Min Range: -2.4337

Max Act: 1.3343. Min Act: -0.0000

Data Index: 311115 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 2.4337. Min Range: -2.4337

Max Act: 1.3747. Min Act: -0.0000

Data Index: 610358 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 2.4337. Min Range: -2.4337

Max Act: 1.2538. Min Act: -0.0000

Data Index: 962957 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 2.4337. Min Range: -2.4337

Max Act: 1.2802. Min Act: -0.0000

Data Index: 329758 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 2.4337. Min Range: -2.4337

Max Act: 1.2580. Min Act: -0.0000

Data Index: 905386 (C4 (Web Text))

Max Activating Token Index: 517