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

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

Neuron 1067 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.5347. Min Act: -0.0000

Data Index: 1338631 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.5148. Min Act: -0.0000

Data Index: 1532585 (Python Code)

Max Activating Token Index: 258

Text #2

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.2654. Min Act: -0.0000

Data Index: 1497979 (Python Code)

Max Activating Token Index: 888

Text #3

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.3129. Min Act: -0.0000

Data Index: 967558 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.2740. Min Act: -0.0000

Data Index: 1542699 (Python Code)

Max Activating Token Index: 367

Text #5

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.3505. Min Act: -0.0000

Data Index: 1485489 (Python Code)

Max Activating Token Index: 708

Text #6

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.1460. Min Act: -0.0000

Data Index: 1255803 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.1108. Min Act: -0.0000

Data Index: 936823 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.1592. Min Act: -0.0000

Data Index: 256634 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.1497. Min Act: -0.0000

Data Index: 478466 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.0802. Min Act: -0.0000

Data Index: 1479546 (Python Code)

Max Activating Token Index: 367

Text #11

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.0941. Min Act: -0.0000

Data Index: 634370 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.0234. Min Act: -0.0000

Data Index: 1503532 (Python Code)

Max Activating Token Index: 907

Text #13

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.1265. Min Act: -0.0000

Data Index: 109023 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.0444. Min Act: -0.0000

Data Index: 735400 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.0321. Min Act: -0.0000

Data Index: 133934 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.0367. Min Act: -0.0000

Data Index: 68314 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 1.5347. Min Range: -1.5347

Max Act: 0.9516. Min Act: -0.0000

Data Index: 1618408 (Python Code)

Max Activating Token Index: 178

Text #18

Max Range: 1.5347. Min Range: -1.5347

Max Act: 0.9319. Min Act: -0.0000

Data Index: 1401621 (Python Code)

Max Activating Token Index: 277

Text #19

Max Range: 1.5347. Min Range: -1.5347

Max Act: 1.0046. Min Act: -0.0000

Data Index: 1223652 (C4 (Web Text))

Max Activating Token Index: 219