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

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

Neuron 10 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: 2.8681. Min Range: -2.8681

Max Act: 2.8681. Min Act: -0.1700

Data Index: 1100369 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.8506. Min Act: -0.1700

Data Index: 431676 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.8082. Min Act: -0.1700

Data Index: 763932 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.7347. Min Act: -0.1700

Data Index: 566371 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.7327. Min Act: -0.1700

Data Index: 832991 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.7108. Min Act: -0.1700

Data Index: 464020 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.6913. Min Act: -0.1700

Data Index: 561127 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.6664. Min Act: -0.1700

Data Index: 1174543 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.6740. Min Act: -0.1700

Data Index: 360588 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.6460. Min Act: -0.1700

Data Index: 1073337 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.6643. Min Act: -0.1700

Data Index: 671209 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.6528. Min Act: -0.1700

Data Index: 463342 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.6558. Min Act: -0.1700

Data Index: 1013 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.6384. Min Act: -0.1700

Data Index: 1244379 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.6305. Min Act: -0.1700

Data Index: 1305018 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.6464. Min Act: -0.1700

Data Index: 1063862 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.6383. Min Act: -0.1700

Data Index: 984095 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.6318. Min Act: -0.1700

Data Index: 1323872 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.6493. Min Act: -0.1700

Data Index: 1228678 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.6107. Min Act: -0.1700

Data Index: 610280 (C4 (Web Text))

Max Activating Token Index: 1013