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

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

Neuron 1755 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: 3.0266. Min Range: -3.0266

Max Act: 3.0266. Min Act: -0.1700

Data Index: 489765 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 3.0266. Min Range: -3.0266

Max Act: 2.8918. Min Act: -0.1700

Data Index: 1104679 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 3.0266. Min Range: -3.0266

Max Act: 2.8684. Min Act: -0.1700

Data Index: 1422502 (Python Code)

Max Activating Token Index: 601

Text #3

Max Range: 3.0266. Min Range: -3.0266

Max Act: 2.8266. Min Act: -0.1700

Data Index: 1161340 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 3.0266. Min Range: -3.0266

Max Act: 2.8380. Min Act: -0.1700

Data Index: 1513500 (Python Code)

Max Activating Token Index: 506

Text #5

Max Range: 3.0266. Min Range: -3.0266

Max Act: 2.8169. Min Act: -0.1700

Data Index: 1452631 (Python Code)

Max Activating Token Index: 963

Text #6

Max Range: 3.0266. Min Range: -3.0266

Max Act: 2.8427. Min Act: -0.1700

Data Index: 363680 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 3.0266. Min Range: -3.0266

Max Act: 2.8386. Min Act: -0.1700

Data Index: 541864 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 3.0266. Min Range: -3.0266

Max Act: 2.7986. Min Act: -0.1700

Data Index: 1372748 (Python Code)

Max Activating Token Index: 89

Text #9

Max Range: 3.0266. Min Range: -3.0266

Max Act: 2.8014. Min Act: -0.1700

Data Index: 1654116 (Python Code)

Max Activating Token Index: 118

Text #10

Max Range: 3.0266. Min Range: -3.0266

Max Act: 2.8194. Min Act: -0.1700

Data Index: 558782 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 3.0266. Min Range: -3.0266

Max Act: 2.8019. Min Act: -0.1700

Data Index: 1328212 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 3.0266. Min Range: -3.0266

Max Act: 2.8295. Min Act: -0.1700

Data Index: 1017190 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 3.0266. Min Range: -3.0266

Max Act: 2.7889. Min Act: -0.1700

Data Index: 538611 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 3.0266. Min Range: -3.0266

Max Act: 2.7745. Min Act: -0.1700

Data Index: 1515786 (Python Code)

Max Activating Token Index: 186

Text #15

Max Range: 3.0266. Min Range: -3.0266

Max Act: 2.7648. Min Act: -0.1700

Data Index: 1542894 (Python Code)

Max Activating Token Index: 414

Text #16

Max Range: 3.0266. Min Range: -3.0266

Max Act: 2.7733. Min Act: -0.1700

Data Index: 1376413 (Python Code)

Max Activating Token Index: 428

Text #17

Max Range: 3.0266. Min Range: -3.0266

Max Act: 2.7773. Min Act: -0.1700

Data Index: 987925 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 3.0266. Min Range: -3.0266

Max Act: 2.7925. Min Act: -0.1700

Data Index: 217759 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 3.0266. Min Range: -3.0266

Max Act: 2.7850. Min Act: -0.1700

Data Index: 1467445 (Python Code)

Max Activating Token Index: 927