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

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

Neuron 5130 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 3.6408. Min Range: -3.6408

Max Act: 3.6408. Min Act: -0.0002

Data Index: 1491677 (Python Code)

Max Activating Token Index: 163

Text #1

Max Range: 3.6408. Min Range: -3.6408

Max Act: 3.5050. Min Act: -0.0002

Data Index: 1404646 (Python Code)

Max Activating Token Index: 1021

Text #2

Max Range: 3.6408. Min Range: -3.6408

Max Act: 3.2871. Min Act: -0.0002

Data Index: 1499223 (Python Code)

Max Activating Token Index: 263

Text #3

Max Range: 3.6408. Min Range: -3.6408

Max Act: 3.3405. Min Act: -0.0002

Data Index: 1641291 (Python Code)

Max Activating Token Index: 995

Text #4

Max Range: 3.6408. Min Range: -3.6408

Max Act: 3.2584. Min Act: -0.0002

Data Index: 1400645 (Python Code)

Max Activating Token Index: 995

Text #5

Max Range: 3.6408. Min Range: -3.6408

Max Act: 3.0581. Min Act: -0.0002

Data Index: 1389300 (Python Code)

Max Activating Token Index: 960

Text #6

Max Range: 3.6408. Min Range: -3.6408

Max Act: 3.1084. Min Act: -0.0002

Data Index: 1475966 (Python Code)

Max Activating Token Index: 961

Text #7

Max Range: 3.6408. Min Range: -3.6408

Max Act: 3.0789. Min Act: -0.0002

Data Index: 1474530 (Python Code)

Max Activating Token Index: 48

Text #8

Max Range: 3.6408. Min Range: -3.6408

Max Act: 3.0858. Min Act: -0.0002

Data Index: 1428372 (Python Code)

Max Activating Token Index: 77

Text #9

Max Range: 3.6408. Min Range: -3.6408

Max Act: 3.1300. Min Act: -0.0002

Data Index: 1622520 (Python Code)

Max Activating Token Index: 126

Text #10

Max Range: 3.6408. Min Range: -3.6408

Max Act: 2.9725. Min Act: -0.0002

Data Index: 1401202 (Python Code)

Max Activating Token Index: 426

Text #11

Max Range: 3.6408. Min Range: -3.6408

Max Act: 3.0105. Min Act: -0.0002

Data Index: 1605123 (Python Code)

Max Activating Token Index: 1022

Text #12

Max Range: 3.6408. Min Range: -3.6408

Max Act: 3.0604. Min Act: -0.0002

Data Index: 1637980 (Python Code)

Max Activating Token Index: 770

Text #13

Max Range: 3.6408. Min Range: -3.6408

Max Act: 3.0767. Min Act: -0.0002

Data Index: 1417829 (Python Code)

Max Activating Token Index: 862

Text #14

Max Range: 3.6408. Min Range: -3.6408

Max Act: 2.9491. Min Act: -0.0002

Data Index: 1616290 (Python Code)

Max Activating Token Index: 960

Text #15

Max Range: 3.6408. Min Range: -3.6408

Max Act: 2.9509. Min Act: -0.0002

Data Index: 1534763 (Python Code)

Max Activating Token Index: 213

Text #16

Max Range: 3.6408. Min Range: -3.6408

Max Act: 3.0177. Min Act: -0.0002

Data Index: 1545115 (Python Code)

Max Activating Token Index: 951

Text #17

Max Range: 3.6408. Min Range: -3.6408

Max Act: 2.9889. Min Act: -0.0002

Data Index: 1361479 (Python Code)

Max Activating Token Index: 309

Text #18

Max Range: 3.6408. Min Range: -3.6408

Max Act: 2.9531. Min Act: -0.0002

Data Index: 1504359 (Python Code)

Max Activating Token Index: 1010

Text #19

Max Range: 3.6408. Min Range: -3.6408

Max Act: 3.0486. Min Act: -0.0002

Data Index: 1654861 (Python Code)

Max Activating Token Index: 122