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

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

Neuron 5724 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7457. Min Range: -4.7457

Max Act: 4.7457. Min Act: -0.0000

Data Index: 682645 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 4.7457. Min Range: -4.7457

Max Act: 3.2586. Min Act: -0.0000

Data Index: 252297 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 4.7457. Min Range: -4.7457

Max Act: 3.1240. Min Act: -0.0000

Data Index: 1286234 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 4.7457. Min Range: -4.7457

Max Act: 3.1463. Min Act: -0.0000

Data Index: 314622 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 4.7457. Min Range: -4.7457

Max Act: 2.7430. Min Act: -0.0000

Data Index: 138500 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 4.7457. Min Range: -4.7457

Max Act: 2.6439. Min Act: -0.0000

Data Index: 3428 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 4.7457. Min Range: -4.7457

Max Act: 2.7791. Min Act: -0.0000

Data Index: 25012 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 4.7457. Min Range: -4.7457

Max Act: 2.6113. Min Act: -0.0000

Data Index: 826052 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 4.7457. Min Range: -4.7457

Max Act: 2.5075. Min Act: -0.0000

Data Index: 20675 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 4.7457. Min Range: -4.7457

Max Act: 2.4026. Min Act: -0.0000

Data Index: 882290 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 4.7457. Min Range: -4.7457

Max Act: 2.4736. Min Act: -0.0000

Data Index: 1163513 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 4.7457. Min Range: -4.7457

Max Act: 2.0901. Min Act: -0.0000

Data Index: 307216 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 4.7457. Min Range: -4.7457

Max Act: 2.3104. Min Act: -0.0000

Data Index: 451900 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 4.7457. Min Range: -4.7457

Max Act: 2.2708. Min Act: 0.0000

Data Index: 1009768 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 4.7457. Min Range: -4.7457

Max Act: 2.2789. Min Act: -0.0000

Data Index: 389785 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 4.7457. Min Range: -4.7457

Max Act: 2.3859. Min Act: -0.0000

Data Index: 876265 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 4.7457. Min Range: -4.7457

Max Act: 2.2431. Min Act: -0.0000

Data Index: 326511 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 4.7457. Min Range: -4.7457

Max Act: 2.3531. Min Act: -0.0000

Data Index: 200957 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 4.7457. Min Range: -4.7457

Max Act: 2.3328. Min Act: -0.0000

Data Index: 674048 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 4.7457. Min Range: -4.7457

Max Act: 2.2290. Min Act: -0.0000

Data Index: 349128 (C4 (Web Text))

Max Activating Token Index: 159