Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 683 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.8674. Min Act: -0.1700

Data Index: 914550 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.8048. Min Act: -0.1700

Data Index: 1505511 (Python Code)

Max Activating Token Index: 300

Text #2

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.6797. Min Act: -0.1700

Data Index: 163422 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.6797. Min Act: -0.1700

Data Index: 1655691 (Python Code)

Max Activating Token Index: 377

Text #4

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.6797. Min Act: -0.1700

Data Index: 400159 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.6797. Min Act: -0.1700

Data Index: 763658 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.6171. Min Act: -0.1700

Data Index: 743530 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.6171. Min Act: -0.1700

Data Index: 1156752 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.5544. Min Act: -0.1700

Data Index: 996809 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.4918. Min Act: -0.1700

Data Index: 735818 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.5544. Min Act: -0.1700

Data Index: 29861 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.5544. Min Act: -0.1700

Data Index: 895292 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.5544. Min Act: -0.1700

Data Index: 429056 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.5544. Min Act: -0.1700

Data Index: 1174274 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.5544. Min Act: -0.1700

Data Index: 1152131 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.5544. Min Act: -0.1700

Data Index: 605488 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.4918. Min Act: -0.1700

Data Index: 1446802 (Python Code)

Max Activating Token Index: 937

Text #17

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.5544. Min Act: -0.1700

Data Index: 1387489 (Python Code)

Max Activating Token Index: 785

Text #18

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.4918. Min Act: -0.1700

Data Index: 1368531 (Python Code)

Max Activating Token Index: 620

Text #19

Max Range: 3.8674. Min Range: -3.8674

Max Act: 3.4291. Min Act: -0.1700

Data Index: 1556639 (Python Code)

Max Activating Token Index: 315