Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1738 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.5643. Min Act: -0.0001

Data Index: 134248 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.5454. Min Act: -0.0001

Data Index: 1339262 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.5105. Min Act: -0.0001

Data Index: 1079495 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.5231. Min Act: -0.0001

Data Index: 316111 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.5504. Min Act: -0.0001

Data Index: 698553 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.5091. Min Act: -0.0001

Data Index: 993575 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4778. Min Act: -0.0001

Data Index: 772304 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.5175. Min Act: -0.0001

Data Index: 1163377 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4343. Min Act: -0.0001

Data Index: 260308 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4615. Min Act: -0.0001

Data Index: 137750 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4692. Min Act: -0.0001

Data Index: 1354647 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4498. Min Act: -0.0001

Data Index: 786771 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4670. Min Act: -0.0001

Data Index: 998088 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4347. Min Act: -0.0001

Data Index: 827283 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4268. Min Act: -0.0001

Data Index: 624775 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4409. Min Act: -0.0001

Data Index: 161061 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4424. Min Act: -0.0001

Data Index: 393989 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4491. Min Act: -0.0001

Data Index: 557054 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4061. Min Act: -0.0001

Data Index: 75053 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4150. Min Act: -0.0001

Data Index: 1262324 (C4 (Web Text))

Max Activating Token Index: 854