Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2165 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.6938. Min Act: -0.0001

Data Index: 116089 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.6493. Min Act: -0.0001

Data Index: 808202 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.5409. Min Act: -0.0001

Data Index: 660188 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.5931. Min Act: -0.0001

Data Index: 110393 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.5399. Min Act: -0.0001

Data Index: 370392 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.5140. Min Act: -0.0001

Data Index: 133811 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.5582. Min Act: -0.0001

Data Index: 408341 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.5211. Min Act: -0.0001

Data Index: 200026 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.4960. Min Act: -0.0001

Data Index: 1312272 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.5263. Min Act: -0.0001

Data Index: 524090 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.4687. Min Act: -0.0001

Data Index: 536654 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.5255. Min Act: -0.0001

Data Index: 508822 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.4618. Min Act: -0.0001

Data Index: 1112734 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.4809. Min Act: -0.0001

Data Index: 549403 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.4341. Min Act: -0.0001

Data Index: 585477 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.4055. Min Act: -0.0001

Data Index: 813648 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.4366. Min Act: -0.0001

Data Index: 375851 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.4617. Min Act: -0.0001

Data Index: 708479 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.4531. Min Act: -0.0001

Data Index: 1267736 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 0.6938. Min Range: -0.6938

Max Act: 0.4576. Min Act: -0.0001

Data Index: 107098 (C4 (Web Text))

Max Activating Token Index: 181