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

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

Neuron 331 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: 2.5572. Min Range: -2.5572

Max Act: 2.5572. Min Act: -0.1700

Data Index: 1605283 (Python Code)

Max Activating Token Index: 565

Text #1

Max Range: 2.5572. Min Range: -2.5572

Max Act: 2.5179. Min Act: -0.1700

Data Index: 1458991 (Python Code)

Max Activating Token Index: 466

Text #2

Max Range: 2.5572. Min Range: -2.5572

Max Act: 2.4850. Min Act: -0.1699

Data Index: 1397382 (Python Code)

Max Activating Token Index: 1018

Text #3

Max Range: 2.5572. Min Range: -2.5572

Max Act: 2.4780. Min Act: -0.1700

Data Index: 357459 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 2.5572. Min Range: -2.5572

Max Act: 2.4090. Min Act: -0.1700

Data Index: 895980 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 2.5572. Min Range: -2.5572

Max Act: 2.4079. Min Act: -0.1700

Data Index: 603827 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 2.5572. Min Range: -2.5572

Max Act: 2.4044. Min Act: -0.1699

Data Index: 1038311 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 2.5572. Min Range: -2.5572

Max Act: 2.3921. Min Act: -0.1687

Data Index: 1569085 (Python Code)

Max Activating Token Index: 357

Text #8

Max Range: 2.5572. Min Range: -2.5572

Max Act: 2.3687. Min Act: -0.1700

Data Index: 358887 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 2.5572. Min Range: -2.5572

Max Act: 2.3551. Min Act: -0.1699

Data Index: 214541 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 2.5572. Min Range: -2.5572

Max Act: 2.3416. Min Act: -0.1700

Data Index: 109004 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 2.5572. Min Range: -2.5572

Max Act: 2.3552. Min Act: -0.1699

Data Index: 1630249 (Python Code)

Max Activating Token Index: 1009

Text #12

Max Range: 2.5572. Min Range: -2.5572

Max Act: 2.3464. Min Act: -0.1700

Data Index: 1369839 (Python Code)

Max Activating Token Index: 623

Text #13

Max Range: 2.5572. Min Range: -2.5572

Max Act: 2.3449. Min Act: -0.1700

Data Index: 131756 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 2.5572. Min Range: -2.5572

Max Act: 2.3476. Min Act: -0.1699

Data Index: 859672 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 2.5572. Min Range: -2.5572

Max Act: 2.3397. Min Act: -0.1698

Data Index: 243556 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 2.5572. Min Range: -2.5572

Max Act: 2.3378. Min Act: -0.1700

Data Index: 125416 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 2.5572. Min Range: -2.5572

Max Act: 2.3419. Min Act: -0.1700

Data Index: 103974 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 2.5572. Min Range: -2.5572

Max Act: 2.3298. Min Act: -0.1700

Data Index: 841658 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 2.5572. Min Range: -2.5572

Max Act: 2.3166. Min Act: -0.1700

Data Index: 1062745 (C4 (Web Text))

Max Activating Token Index: 239