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

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

Neuron 546 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: 3.5426. Min Range: -3.5426

Max Act: 3.5426. Min Act: -0.1700

Data Index: 920140 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.5022. Min Act: -0.1700

Data Index: 863824 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.4454. Min Act: -0.1700

Data Index: 218231 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.4525. Min Act: -0.1700

Data Index: 1305424 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.4357. Min Act: -0.1700

Data Index: 1272080 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.4491. Min Act: -0.1700

Data Index: 1076284 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.3866. Min Act: -0.1700

Data Index: 697045 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.4018. Min Act: -0.1700

Data Index: 410380 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.4234. Min Act: -0.1700

Data Index: 793616 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.3919. Min Act: -0.1700

Data Index: 254974 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.3929. Min Act: -0.1700

Data Index: 42308 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.3735. Min Act: -0.1700

Data Index: 182455 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.3686. Min Act: -0.1700

Data Index: 360244 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.3432. Min Act: -0.1700

Data Index: 460421 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.3539. Min Act: -0.1700

Data Index: 1269311 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.3038. Min Act: -0.1700

Data Index: 779123 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.3241. Min Act: -0.1700

Data Index: 692644 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.3321. Min Act: -0.1700

Data Index: 577089 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.3164. Min Act: -0.1700

Data Index: 314918 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.3359. Min Act: -0.1700

Data Index: 627474 (C4 (Web Text))

Max Activating Token Index: 641