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

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

Neuron 1934 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: 4.4298. Min Range: -4.4298

Max Act: 4.3874. Min Act: -0.1700

Data Index: 411690 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 4.4298. Min Range: -4.4298

Max Act: 4.4298. Min Act: -0.1700

Data Index: 1312378 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 4.4298. Min Range: -4.4298

Max Act: 4.4151. Min Act: -0.1700

Data Index: 293138 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 4.4298. Min Range: -4.4298

Max Act: 4.3793. Min Act: -0.1700

Data Index: 322995 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 4.4298. Min Range: -4.4298

Max Act: 4.3559. Min Act: -0.1700

Data Index: 1123595 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 4.4298. Min Range: -4.4298

Max Act: 4.3117. Min Act: -0.1700

Data Index: 601557 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 4.4298. Min Range: -4.4298

Max Act: 4.2768. Min Act: -0.1700

Data Index: 1412045 (Python Code)

Max Activating Token Index: 262

Text #7

Max Range: 4.4298. Min Range: -4.4298

Max Act: 4.3067. Min Act: -0.1700

Data Index: 1403618 (Python Code)

Max Activating Token Index: 615

Text #8

Max Range: 4.4298. Min Range: -4.4298

Max Act: 4.3075. Min Act: -0.1700

Data Index: 1656927 (Python Code)

Max Activating Token Index: 481

Text #9

Max Range: 4.4298. Min Range: -4.4298

Max Act: 4.2983. Min Act: -0.1700

Data Index: 770444 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 4.4298. Min Range: -4.4298

Max Act: 4.2599. Min Act: -0.1700

Data Index: 371386 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 4.4298. Min Range: -4.4298

Max Act: 4.2568. Min Act: -0.1700

Data Index: 496523 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 4.4298. Min Range: -4.4298

Max Act: 4.2450. Min Act: -0.1700

Data Index: 404609 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 4.4298. Min Range: -4.4298

Max Act: 4.2399. Min Act: -0.1700

Data Index: 449213 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 4.4298. Min Range: -4.4298

Max Act: 4.2512. Min Act: -0.1700

Data Index: 1374673 (Python Code)

Max Activating Token Index: 712

Text #15

Max Range: 4.4298. Min Range: -4.4298

Max Act: 4.2364. Min Act: -0.1699

Data Index: 1506889 (Python Code)

Max Activating Token Index: 695

Text #16

Max Range: 4.4298. Min Range: -4.4298

Max Act: 4.2287. Min Act: -0.1700

Data Index: 467262 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 4.4298. Min Range: -4.4298

Max Act: 4.2348. Min Act: -0.1700

Data Index: 948438 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 4.4298. Min Range: -4.4298

Max Act: 4.2022. Min Act: -0.1700

Data Index: 1000552 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 4.4298. Min Range: -4.4298

Max Act: 4.2175. Min Act: -0.1700

Data Index: 1214753 (C4 (Web Text))

Max Activating Token Index: 174