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

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

Neuron 1431 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: 3.4276. Min Range: -3.4276

Max Act: 3.4276. Min Act: -0.1700

Data Index: 1426269 (Python Code)

Max Activating Token Index: 781

Text #1

Max Range: 3.4276. Min Range: -3.4276

Max Act: 3.2597. Min Act: -0.1700

Data Index: 1413388 (Python Code)

Max Activating Token Index: 169

Text #2

Max Range: 3.4276. Min Range: -3.4276

Max Act: 3.2381. Min Act: -0.1700

Data Index: 1367745 (Python Code)

Max Activating Token Index: 977

Text #3

Max Range: 3.4276. Min Range: -3.4276

Max Act: 3.1660. Min Act: -0.1700

Data Index: 276571 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 3.4276. Min Range: -3.4276

Max Act: 3.1556. Min Act: -0.1700

Data Index: 1317040 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 3.4276. Min Range: -3.4276

Max Act: 3.1519. Min Act: -0.1700

Data Index: 1160588 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 3.4276. Min Range: -3.4276

Max Act: 3.1306. Min Act: -0.1700

Data Index: 141800 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 3.4276. Min Range: -3.4276

Max Act: 3.1096. Min Act: -0.1700

Data Index: 479772 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 3.4276. Min Range: -3.4276

Max Act: 3.0807. Min Act: -0.1700

Data Index: 397010 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 3.4276. Min Range: -3.4276

Max Act: 3.0895. Min Act: -0.1700

Data Index: 1605443 (Python Code)

Max Activating Token Index: 353

Text #10

Max Range: 3.4276. Min Range: -3.4276

Max Act: 3.0637. Min Act: -0.1700

Data Index: 1517030 (Python Code)

Max Activating Token Index: 361

Text #11

Max Range: 3.4276. Min Range: -3.4276

Max Act: 3.0686. Min Act: -0.1700

Data Index: 1276410 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 3.4276. Min Range: -3.4276

Max Act: 3.0400. Min Act: -0.1700

Data Index: 1451333 (Python Code)

Max Activating Token Index: 618

Text #13

Max Range: 3.4276. Min Range: -3.4276

Max Act: 3.0440. Min Act: -0.1700

Data Index: 521550 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 3.4276. Min Range: -3.4276

Max Act: 3.0469. Min Act: -0.1700

Data Index: 433517 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 3.4276. Min Range: -3.4276

Max Act: 3.0435. Min Act: -0.1700

Data Index: 158323 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 3.4276. Min Range: -3.4276

Max Act: 3.0535. Min Act: -0.1700

Data Index: 697190 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 3.4276. Min Range: -3.4276

Max Act: 3.0382. Min Act: -0.1700

Data Index: 435727 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 3.4276. Min Range: -3.4276

Max Act: 3.0430. Min Act: -0.1700

Data Index: 1488799 (Python Code)

Max Activating Token Index: 15

Text #19

Max Range: 3.4276. Min Range: -3.4276

Max Act: 3.0347. Min Act: -0.1700

Data Index: 182233 (C4 (Web Text))

Max Activating Token Index: 102