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

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

Neuron 124 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0700. Min Act: -0.0002

Data Index: 1297476 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0626. Min Act: -0.0002

Data Index: 93662 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0573. Min Act: -0.0002

Data Index: 584023 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0551. Min Act: -0.0002

Data Index: 898088 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1051338 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1004464 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0475. Min Act: -0.0002

Data Index: 147374 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0488. Min Act: -0.0002

Data Index: 234771 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0474. Min Act: -0.0002

Data Index: 724427 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0468. Min Act: -0.0002

Data Index: 160189 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0459. Min Act: -0.0002

Data Index: 647273 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1130527 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1351334 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1229996 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0451. Min Act: -0.0002

Data Index: 383284 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0440. Min Act: -0.0002

Data Index: 497904 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0457. Min Act: -0.0002

Data Index: 582231 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0430. Min Act: -0.0002

Data Index: 418788 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0439. Min Act: -0.0002

Data Index: 28044 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0437. Min Act: -0.0002

Data Index: 841563 (C4 (Web Text))

Max Activating Token Index: 204