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

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

Neuron 1690 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: 0.3172. Min Range: -0.3172

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1125851 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2776. Min Act: -0.0000

Data Index: 1538773 (Python Code)

Max Activating Token Index: 477

Text #2

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2504. Min Act: -0.0000

Data Index: 125269 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2880. Min Act: -0.0000

Data Index: 1278429 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2704. Min Act: -0.0000

Data Index: 505049 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2835. Min Act: -0.0000

Data Index: 70740 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2499. Min Act: -0.0000

Data Index: 291263 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1056325 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2534. Min Act: -0.0000

Data Index: 955391 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2341. Min Act: -0.0000

Data Index: 1286720 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2638. Min Act: -0.0000

Data Index: 216371 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2436. Min Act: -0.0000

Data Index: 319327 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2505. Min Act: -0.0000

Data Index: 1279750 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2486. Min Act: -0.0000

Data Index: 583394 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2484. Min Act: -0.0000

Data Index: 736479 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2029. Min Act: -0.0000

Data Index: 1446343 (Python Code)

Max Activating Token Index: 802

Text #16

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2061. Min Act: -0.0000

Data Index: 1151764 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2320. Min Act: -0.0000

Data Index: 1115578 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2330. Min Act: -0.0000

Data Index: 764388 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2427. Min Act: -0.0000

Data Index: 71944 (C4 (Web Text))

Max Activating Token Index: 663