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

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

Neuron 1868 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: 3.4196. Min Range: -3.4196

Max Act: 3.4196. Min Act: -0.1700

Data Index: 1528572 (Python Code)

Max Activating Token Index: 193

Text #1

Max Range: 3.4196. Min Range: -3.4196

Max Act: 3.3554. Min Act: -0.1700

Data Index: 1257764 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 3.4196. Min Range: -3.4196

Max Act: 3.3021. Min Act: -0.1700

Data Index: 1031974 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 3.4196. Min Range: -3.4196

Max Act: 3.3038. Min Act: -0.1700

Data Index: 884414 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 3.4196. Min Range: -3.4196

Max Act: 3.2626. Min Act: -0.1700

Data Index: 656537 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 3.4196. Min Range: -3.4196

Max Act: 3.2655. Min Act: -0.1700

Data Index: 1541783 (Python Code)

Max Activating Token Index: 712

Text #6

Max Range: 3.4196. Min Range: -3.4196

Max Act: 3.2293. Min Act: -0.1700

Data Index: 908654 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 3.4196. Min Range: -3.4196

Max Act: 3.2493. Min Act: -0.1700

Data Index: 1578296 (Python Code)

Max Activating Token Index: 874

Text #8

Max Range: 3.4196. Min Range: -3.4196

Max Act: 3.2540. Min Act: -0.1700

Data Index: 1612673 (Python Code)

Max Activating Token Index: 879

Text #9

Max Range: 3.4196. Min Range: -3.4196

Max Act: 3.2573. Min Act: -0.1700

Data Index: 1621452 (Python Code)

Max Activating Token Index: 326

Text #10

Max Range: 3.4196. Min Range: -3.4196

Max Act: 3.2314. Min Act: -0.1700

Data Index: 570048 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 3.4196. Min Range: -3.4196

Max Act: 3.2291. Min Act: -0.1700

Data Index: 244844 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 3.4196. Min Range: -3.4196

Max Act: 3.2219. Min Act: -0.1700

Data Index: 314878 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 3.4196. Min Range: -3.4196

Max Act: 3.2094. Min Act: -0.1700

Data Index: 1134774 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 3.4196. Min Range: -3.4196

Max Act: 3.1993. Min Act: -0.1700

Data Index: 1651790 (Python Code)

Max Activating Token Index: 447

Text #15

Max Range: 3.4196. Min Range: -3.4196

Max Act: 3.1947. Min Act: -0.1700

Data Index: 430137 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 3.4196. Min Range: -3.4196

Max Act: 3.1609. Min Act: -0.1700

Data Index: 192912 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 3.4196. Min Range: -3.4196

Max Act: 3.1841. Min Act: -0.1700

Data Index: 1471022 (Python Code)

Max Activating Token Index: 329

Text #18

Max Range: 3.4196. Min Range: -3.4196

Max Act: 3.1913. Min Act: -0.1700

Data Index: 1482396 (Python Code)

Max Activating Token Index: 186

Text #19

Max Range: 3.4196. Min Range: -3.4196

Max Act: 3.1997. Min Act: -0.1700

Data Index: 1432987 (Python Code)

Max Activating Token Index: 954