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

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

Neuron 1514 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1950. Min Range: -5.1950

Max Act: 5.1950. Min Act: -0.1700

Data Index: 98271 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 5.1950. Min Range: -5.1950

Max Act: 5.1638. Min Act: -0.1700

Data Index: 1083277 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 5.1950. Min Range: -5.1950

Max Act: 5.1013. Min Act: -0.1700

Data Index: 423968 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 5.1950. Min Range: -5.1950

Max Act: 5.1325. Min Act: -0.1700

Data Index: 540890 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 5.1950. Min Range: -5.1950

Max Act: 5.0075. Min Act: -0.1700

Data Index: 1269167 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 5.1950. Min Range: -5.1950

Max Act: 5.0075. Min Act: -0.1700

Data Index: 27243 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 5.1950. Min Range: -5.1950

Max Act: 5.0700. Min Act: -0.1700

Data Index: 1227081 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 5.1950. Min Range: -5.1950

Max Act: 5.0075. Min Act: -0.1700

Data Index: 1347642 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 5.1950. Min Range: -5.1950

Max Act: 5.0075. Min Act: -0.1700

Data Index: 621188 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 5.1950. Min Range: -5.1950

Max Act: 4.9763. Min Act: -0.1700

Data Index: 252273 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 5.1950. Min Range: -5.1950

Max Act: 4.9450. Min Act: -0.1700

Data Index: 1133157 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 5.1950. Min Range: -5.1950

Max Act: 5.0075. Min Act: -0.1700

Data Index: 1274069 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 5.1950. Min Range: -5.1950

Max Act: 4.9450. Min Act: -0.1700

Data Index: 1148896 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 5.1950. Min Range: -5.1950

Max Act: 4.9450. Min Act: -0.1700

Data Index: 390311 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 5.1950. Min Range: -5.1950

Max Act: 4.9138. Min Act: -0.1700

Data Index: 655743 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 5.1950. Min Range: -5.1950

Max Act: 4.9763. Min Act: -0.1700

Data Index: 751667 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 5.1950. Min Range: -5.1950

Max Act: 4.8825. Min Act: -0.1700

Data Index: 755598 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 5.1950. Min Range: -5.1950

Max Act: 4.9450. Min Act: -0.1700

Data Index: 569327 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 5.1950. Min Range: -5.1950

Max Act: 4.9450. Min Act: -0.1700

Data Index: 459402 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 5.1950. Min Range: -5.1950

Max Act: 4.8513. Min Act: -0.1700

Data Index: 150211 (C4 (Web Text))

Max Activating Token Index: 421