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

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

Neuron 190 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: 0.7174. Min Range: -0.7174

Max Act: 0.7174. Min Act: -0.0000

Data Index: 849318 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5737. Min Act: -0.0000

Data Index: 1321462 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5260. Min Act: -0.0000

Data Index: 389125 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4874. Min Act: -0.0000

Data Index: 113802 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4906. Min Act: -0.0000

Data Index: 843325 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4688. Min Act: -0.0000

Data Index: 164033 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4476. Min Act: -0.0000

Data Index: 361615 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4464. Min Act: -0.0000

Data Index: 179983 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4711. Min Act: -0.0000

Data Index: 33461 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4957. Min Act: -0.0000

Data Index: 1273920 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4576. Min Act: -0.0000

Data Index: 914609 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4756. Min Act: -0.0000

Data Index: 879138 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4628. Min Act: -0.0000

Data Index: 132616 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4514. Min Act: -0.0000

Data Index: 1109713 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4504. Min Act: -0.0000

Data Index: 478737 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4332. Min Act: -0.0000

Data Index: 455784 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4624. Min Act: -0.0000

Data Index: 219972 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4294. Min Act: -0.0000

Data Index: 929008 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1327268 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4505. Min Act: -0.0000

Data Index: 530238 (C4 (Web Text))

Max Activating Token Index: 884