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

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

Neuron 5158 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3220. Min Range: -4.3220

Max Act: 4.2788. Min Act: -0.0000

Data Index: 1071964 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 4.3220. Min Range: -4.3220

Max Act: 4.3220. Min Act: -0.0000

Data Index: 114303 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 4.3220. Min Range: -4.3220

Max Act: 3.7527. Min Act: -0.0000

Data Index: 968623 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 4.3220. Min Range: -4.3220

Max Act: 3.7051. Min Act: -0.0000

Data Index: 595950 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 4.3220. Min Range: -4.3220

Max Act: 3.6682. Min Act: -0.0000

Data Index: 861392 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 4.3220. Min Range: -4.3220

Max Act: 3.4555. Min Act: -0.0000

Data Index: 930413 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 4.3220. Min Range: -4.3220

Max Act: 3.5428. Min Act: -0.0000

Data Index: 616457 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 4.3220. Min Range: -4.3220

Max Act: 3.5102. Min Act: -0.0000

Data Index: 160702 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 4.3220. Min Range: -4.3220

Max Act: 3.4537. Min Act: -0.0000

Data Index: 1137360 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 4.3220. Min Range: -4.3220

Max Act: 3.4145. Min Act: -0.0000

Data Index: 87616 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 4.3220. Min Range: -4.3220

Max Act: 3.4991. Min Act: -0.0000

Data Index: 74620 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 4.3220. Min Range: -4.3220

Max Act: 3.3353. Min Act: -0.0000

Data Index: 925186 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 4.3220. Min Range: -4.3220

Max Act: 3.2761. Min Act: -0.0000

Data Index: 1065437 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 4.3220. Min Range: -4.3220

Max Act: 3.2377. Min Act: -0.0000

Data Index: 260406 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 4.3220. Min Range: -4.3220

Max Act: 3.2207. Min Act: -0.0000

Data Index: 729517 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 4.3220. Min Range: -4.3220

Max Act: 3.3444. Min Act: -0.0000

Data Index: 105467 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 4.3220. Min Range: -4.3220

Max Act: 3.1938. Min Act: -0.0000

Data Index: 329579 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 4.3220. Min Range: -4.3220

Max Act: 3.2886. Min Act: -0.0000

Data Index: 518767 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 4.3220. Min Range: -4.3220

Max Act: 3.2495. Min Act: -0.0000

Data Index: 885940 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 4.3220. Min Range: -4.3220

Max Act: 3.0733. Min Act: -0.0000

Data Index: 1246568 (C4 (Web Text))

Max Activating Token Index: 832