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

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

Neuron 38 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0630. Min Act: -0.0001

Data Index: 415319 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0588. Min Act: -0.0001

Data Index: 1215705 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0606. Min Act: -0.0001

Data Index: 1001386 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0640. Min Act: -0.0001

Data Index: 1105289 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1052908 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0593. Min Act: -0.0001

Data Index: 328084 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0638. Min Act: -0.0001

Data Index: 908596 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0571. Min Act: -0.0001

Data Index: 430194 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0533. Min Act: -0.0001

Data Index: 409630 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0552. Min Act: -0.0001

Data Index: 1299321 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0523. Min Act: -0.0001

Data Index: 841379 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0545. Min Act: -0.0001

Data Index: 333614 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0513. Min Act: -0.0001

Data Index: 1260506 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0483. Min Act: -0.0001

Data Index: 1024545 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0538. Min Act: -0.0001

Data Index: 396704 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0480. Min Act: -0.0001

Data Index: 53696 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0460. Min Act: -0.0001

Data Index: 298915 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0531. Min Act: -0.0001

Data Index: 857804 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0455. Min Act: -0.0001

Data Index: 397802 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0469. Min Act: -0.0001

Data Index: 931851 (C4 (Web Text))

Max Activating Token Index: 280