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

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

Neuron 115 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: 3.8444. Min Range: -3.8444

Max Act: 3.8444. Min Act: -0.1700

Data Index: 873853 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 3.8444. Min Range: -3.8444

Max Act: 3.7349. Min Act: -0.1700

Data Index: 290255 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 3.8444. Min Range: -3.8444

Max Act: 3.6879. Min Act: -0.1700

Data Index: 1199179 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 3.8444. Min Range: -3.8444

Max Act: 3.7036. Min Act: -0.1700

Data Index: 779453 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 3.8444. Min Range: -3.8444

Max Act: 3.6879. Min Act: -0.1700

Data Index: 24585 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 3.8444. Min Range: -3.8444

Max Act: 3.6097. Min Act: -0.1700

Data Index: 554644 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 3.8444. Min Range: -3.8444

Max Act: 3.6097. Min Act: -0.1700

Data Index: 1170840 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 3.8444. Min Range: -3.8444

Max Act: 3.6253. Min Act: -0.1700

Data Index: 1131814 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 3.8444. Min Range: -3.8444

Max Act: 3.6410. Min Act: -0.1700

Data Index: 922108 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 3.8444. Min Range: -3.8444

Max Act: 3.6097. Min Act: -0.1700

Data Index: 407956 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 3.8444. Min Range: -3.8444

Max Act: 3.5784. Min Act: -0.1700

Data Index: 1054226 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 3.8444. Min Range: -3.8444

Max Act: 3.5627. Min Act: -0.1700

Data Index: 380052 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 3.8444. Min Range: -3.8444

Max Act: 3.5627. Min Act: -0.1700

Data Index: 1186704 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 3.8444. Min Range: -3.8444

Max Act: 3.5784. Min Act: -0.1700

Data Index: 502034 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 3.8444. Min Range: -3.8444

Max Act: 3.5784. Min Act: -0.1700

Data Index: 758873 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 3.8444. Min Range: -3.8444

Max Act: 3.5470. Min Act: -0.1700

Data Index: 35885 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 3.8444. Min Range: -3.8444

Max Act: 3.5470. Min Act: -0.1700

Data Index: 760312 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 3.8444. Min Range: -3.8444

Max Act: 3.6097. Min Act: -0.1700

Data Index: 539502 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 3.8444. Min Range: -3.8444

Max Act: 3.5314. Min Act: -0.1700

Data Index: 572393 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 3.8444. Min Range: -3.8444

Max Act: 3.5157. Min Act: -0.1699

Data Index: 980142 (C4 (Web Text))

Max Activating Token Index: 966