Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1889 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.5246. Min Act: -0.1700

Data Index: 638199 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.4932. Min Act: -0.1700

Data Index: 254909 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.4776. Min Act: -0.1700

Data Index: 816461 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.5089. Min Act: -0.1700

Data Index: 515151 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.4619. Min Act: -0.1700

Data Index: 959677 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.4462. Min Act: -0.1700

Data Index: 486 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.4462. Min Act: -0.1700

Data Index: 404448 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.4148. Min Act: -0.1700

Data Index: 339896 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.4148. Min Act: -0.1700

Data Index: 1093962 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.4776. Min Act: -0.1700

Data Index: 1190145 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.4462. Min Act: -0.1700

Data Index: 1183511 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.4462. Min Act: -0.1700

Data Index: 1056259 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.3835. Min Act: -0.1700

Data Index: 1334250 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.4148. Min Act: -0.1700

Data Index: 1238951 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.3678. Min Act: -0.1700

Data Index: 478970 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.3835. Min Act: -0.1700

Data Index: 166719 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.3678. Min Act: -0.1700

Data Index: 1194945 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.3364. Min Act: -0.1700

Data Index: 950890 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.3521. Min Act: -0.1700

Data Index: 849410 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 3.5246. Min Range: -3.5246

Max Act: 3.3678. Min Act: -0.1700

Data Index: 962829 (C4 (Web Text))

Max Activating Token Index: 513