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

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

Neuron 405 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: 4.4756. Min Range: -4.4756

Max Act: 4.4756. Min Act: -0.1700

Data Index: 1405515 (Python Code)

Max Activating Token Index: 395

Text #1

Max Range: 4.4756. Min Range: -4.4756

Max Act: 4.2554. Min Act: -0.1700

Data Index: 1589962 (Python Code)

Max Activating Token Index: 432

Text #2

Max Range: 4.4756. Min Range: -4.4756

Max Act: 4.2429. Min Act: -0.1700

Data Index: 1399621 (Python Code)

Max Activating Token Index: 362

Text #3

Max Range: 4.4756. Min Range: -4.4756

Max Act: 4.1923. Min Act: -0.1700

Data Index: 1460570 (Python Code)

Max Activating Token Index: 944

Text #4

Max Range: 4.4756. Min Range: -4.4756

Max Act: 4.1181. Min Act: -0.1700

Data Index: 1623862 (Python Code)

Max Activating Token Index: 611

Text #5

Max Range: 4.4756. Min Range: -4.4756

Max Act: 4.1132. Min Act: -0.1700

Data Index: 1567991 (Python Code)

Max Activating Token Index: 46

Text #6

Max Range: 4.4756. Min Range: -4.4756

Max Act: 4.0584. Min Act: -0.1700

Data Index: 1398980 (Python Code)

Max Activating Token Index: 121

Text #7

Max Range: 4.4756. Min Range: -4.4756

Max Act: 4.0301. Min Act: -0.1700

Data Index: 93724 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 4.4756. Min Range: -4.4756

Max Act: 3.9859. Min Act: -0.1700

Data Index: 1512177 (Python Code)

Max Activating Token Index: 318

Text #9

Max Range: 4.4756. Min Range: -4.4756

Max Act: 3.9441. Min Act: -0.1700

Data Index: 775871 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 4.4756. Min Range: -4.4756

Max Act: 3.9399. Min Act: -0.1700

Data Index: 1504749 (Python Code)

Max Activating Token Index: 486

Text #11

Max Range: 4.4756. Min Range: -4.4756

Max Act: 3.9279. Min Act: -0.1700

Data Index: 1525243 (Python Code)

Max Activating Token Index: 1014

Text #12

Max Range: 4.4756. Min Range: -4.4756

Max Act: 3.9259. Min Act: -0.1700

Data Index: 1403269 (Python Code)

Max Activating Token Index: 984

Text #13

Max Range: 4.4756. Min Range: -4.4756

Max Act: 3.9233. Min Act: -0.1700

Data Index: 1585510 (Python Code)

Max Activating Token Index: 960

Text #14

Max Range: 4.4756. Min Range: -4.4756

Max Act: 3.9497. Min Act: -0.1700

Data Index: 632687 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 4.4756. Min Range: -4.4756

Max Act: 3.9214. Min Act: -0.1700

Data Index: 1381628 (Python Code)

Max Activating Token Index: 639

Text #16

Max Range: 4.4756. Min Range: -4.4756

Max Act: 3.8946. Min Act: -0.1700

Data Index: 1645556 (Python Code)

Max Activating Token Index: 350

Text #17

Max Range: 4.4756. Min Range: -4.4756

Max Act: 3.9167. Min Act: -0.1699

Data Index: 1410198 (Python Code)

Max Activating Token Index: 269

Text #18

Max Range: 4.4756. Min Range: -4.4756

Max Act: 3.9078. Min Act: -0.1700

Data Index: 1142152 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 4.4756. Min Range: -4.4756

Max Act: 3.8415. Min Act: -0.1698

Data Index: 1544342 (Python Code)

Max Activating Token Index: 459