Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 195 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2946. Min Range: -3.2946

Max Act: 3.2946. Min Act: -0.1700

Data Index: 846413 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 3.2946. Min Range: -3.2946

Max Act: 3.2788. Min Act: -0.1700

Data Index: 435031 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 3.2946. Min Range: -3.2946

Max Act: 3.2631. Min Act: -0.1700

Data Index: 1548495 (Python Code)

Max Activating Token Index: 328

Text #3

Max Range: 3.2946. Min Range: -3.2946

Max Act: 3.2788. Min Act: -0.1700

Data Index: 463450 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 3.2946. Min Range: -3.2946

Max Act: 3.2631. Min Act: -0.1700

Data Index: 500528 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 3.2946. Min Range: -3.2946

Max Act: 3.2474. Min Act: -0.1700

Data Index: 293091 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 3.2946. Min Range: -3.2946

Max Act: 3.2317. Min Act: -0.1700

Data Index: 1546397 (Python Code)

Max Activating Token Index: 176

Text #7

Max Range: 3.2946. Min Range: -3.2946

Max Act: 3.2474. Min Act: -0.1700

Data Index: 25985 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 3.2946. Min Range: -3.2946

Max Act: 3.2474. Min Act: -0.1700

Data Index: 1050190 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 3.2946. Min Range: -3.2946

Max Act: 3.2474. Min Act: -0.1700

Data Index: 468558 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 3.2946. Min Range: -3.2946

Max Act: 3.2002. Min Act: -0.1700

Data Index: 713724 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 3.2946. Min Range: -3.2946

Max Act: 3.2160. Min Act: -0.1700

Data Index: 1640423 (Python Code)

Max Activating Token Index: 4

Text #12

Max Range: 3.2946. Min Range: -3.2946

Max Act: 3.2002. Min Act: -0.1700

Data Index: 144803 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 3.2946. Min Range: -3.2946

Max Act: 3.2160. Min Act: -0.1700

Data Index: 790873 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 3.2946. Min Range: -3.2946

Max Act: 3.2002. Min Act: -0.1700

Data Index: 1189605 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 3.2946. Min Range: -3.2946

Max Act: 3.1845. Min Act: -0.1700

Data Index: 1113941 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 3.2946. Min Range: -3.2946

Max Act: 3.2002. Min Act: -0.1700

Data Index: 270276 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 3.2946. Min Range: -3.2946

Max Act: 3.2002. Min Act: -0.1700

Data Index: 737605 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 3.2946. Min Range: -3.2946

Max Act: 3.1688. Min Act: -0.1700

Data Index: 616047 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 3.2946. Min Range: -3.2946

Max Act: 3.1688. Min Act: -0.1700

Data Index: 210505 (C4 (Web Text))

Max Activating Token Index: 486