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

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

Neuron 1515 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: 3.2934. Min Range: -3.2934

Max Act: 3.2934. Min Act: -0.1700

Data Index: 484070 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 3.2934. Min Range: -3.2934

Max Act: 3.2864. Min Act: -0.1700

Data Index: 957843 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 3.2934. Min Range: -3.2934

Max Act: 3.2625. Min Act: -0.1700

Data Index: 257658 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 3.2934. Min Range: -3.2934

Max Act: 3.2477. Min Act: -0.1700

Data Index: 206240 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 3.2934. Min Range: -3.2934

Max Act: 3.2471. Min Act: -0.1700

Data Index: 250175 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 3.2934. Min Range: -3.2934

Max Act: 3.2579. Min Act: -0.1699

Data Index: 998632 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 3.2934. Min Range: -3.2934

Max Act: 3.2402. Min Act: -0.1700

Data Index: 252788 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 3.2934. Min Range: -3.2934

Max Act: 3.2299. Min Act: -0.1700

Data Index: 295 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 3.2934. Min Range: -3.2934

Max Act: 3.2237. Min Act: -0.1699

Data Index: 274440 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 3.2934. Min Range: -3.2934

Max Act: 3.1884. Min Act: -0.1700

Data Index: 697352 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 3.2934. Min Range: -3.2934

Max Act: 3.1943. Min Act: -0.1698

Data Index: 597902 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 3.2934. Min Range: -3.2934

Max Act: 3.1830. Min Act: -0.1700

Data Index: 1106009 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 3.2934. Min Range: -3.2934

Max Act: 3.1706. Min Act: -0.1700

Data Index: 513236 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 3.2934. Min Range: -3.2934

Max Act: 3.1782. Min Act: -0.1700

Data Index: 645049 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 3.2934. Min Range: -3.2934

Max Act: 3.1712. Min Act: -0.1700

Data Index: 842203 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 3.2934. Min Range: -3.2934

Max Act: 3.1634. Min Act: -0.1700

Data Index: 1140007 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 3.2934. Min Range: -3.2934

Max Act: 3.1649. Min Act: -0.1700

Data Index: 347549 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 3.2934. Min Range: -3.2934

Max Act: 3.1416. Min Act: -0.1700

Data Index: 1614811 (Python Code)

Max Activating Token Index: 706

Text #18

Max Range: 3.2934. Min Range: -3.2934

Max Act: 3.1310. Min Act: -0.1700

Data Index: 1136735 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 3.2934. Min Range: -3.2934

Max Act: 3.1210. Min Act: -0.1700

Data Index: 486319 (C4 (Web Text))

Max Activating Token Index: 570