Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 831 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.4979. Min Range: -3.4979

Max Act: 3.4979. Min Act: -0.1699

Data Index: 1174865 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 3.4979. Min Range: -3.4979

Max Act: 3.4275. Min Act: -0.1700

Data Index: 1167693 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 3.4979. Min Range: -3.4979

Max Act: 3.3804. Min Act: -0.1699

Data Index: 1112510 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 3.4979. Min Range: -3.4979

Max Act: 3.3171. Min Act: -0.1700

Data Index: 1068608 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 3.4979. Min Range: -3.4979

Max Act: 3.2569. Min Act: -0.1700

Data Index: 1581239 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.4979. Min Range: -3.4979

Max Act: 3.2694. Min Act: -0.1700

Data Index: 999933 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 3.4979. Min Range: -3.4979

Max Act: 3.2065. Min Act: -0.1700

Data Index: 1207393 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 3.4979. Min Range: -3.4979

Max Act: 3.2289. Min Act: -0.1700

Data Index: 1535367 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 3.4979. Min Range: -3.4979

Max Act: 3.2076. Min Act: -0.1700

Data Index: 1455387 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 3.4979. Min Range: -3.4979

Max Act: 3.2231. Min Act: -0.1700

Data Index: 1550719 (Python Code)

Max Activating Token Index: 514

Text #10

Max Range: 3.4979. Min Range: -3.4979

Max Act: 3.1885. Min Act: -0.1700

Data Index: 1654148 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 3.4979. Min Range: -3.4979

Max Act: 3.2052. Min Act: -0.1700

Data Index: 1406803 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 3.4979. Min Range: -3.4979

Max Act: 3.2306. Min Act: -0.1699

Data Index: 972601 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 3.4979. Min Range: -3.4979

Max Act: 3.2210. Min Act: -0.1700

Data Index: 327379 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 3.4979. Min Range: -3.4979

Max Act: 3.2029. Min Act: -0.1699

Data Index: 414625 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 3.4979. Min Range: -3.4979

Max Act: 3.2086. Min Act: -0.1700

Data Index: 756127 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 3.4979. Min Range: -3.4979

Max Act: 3.2074. Min Act: -0.1700

Data Index: 998874 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 3.4979. Min Range: -3.4979

Max Act: 3.2353. Min Act: -0.1700

Data Index: 160900 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 3.4979. Min Range: -3.4979

Max Act: 3.2326. Min Act: -0.1700

Data Index: 483211 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 3.4979. Min Range: -3.4979

Max Act: 3.2098. Min Act: -0.1700

Data Index: 51331 (C4 (Web Text))

Max Activating Token Index: 946