Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 723 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.5582. Min Act: -0.1700

Data Index: 1518523 (Open Web Text)

Max Activating Token Index: 394

Text #1

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.4493. Min Act: -0.1700

Data Index: 4957370 (Open Web Text)

Max Activating Token Index: 547

Text #2

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.4504. Min Act: -0.1700

Data Index: 794471 (Open Web Text)

Max Activating Token Index: 935

Text #3

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.4253. Min Act: -0.1700

Data Index: 5282422 (Open Web Text)

Max Activating Token Index: 739

Text #4

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.4346. Min Act: -0.1700

Data Index: 5509748 (Open Web Text)

Max Activating Token Index: 870

Text #5

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.4572. Min Act: -0.1700

Data Index: 6244542 (Open Web Text)

Max Activating Token Index: 746

Text #6

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.4404. Min Act: -0.1700

Data Index: 2894382 (Open Web Text)

Max Activating Token Index: 485

Text #7

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.4217. Min Act: -0.1700

Data Index: 2824142 (Open Web Text)

Max Activating Token Index: 974

Text #8

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.4063. Min Act: -0.1700

Data Index: 1560339 (Open Web Text)

Max Activating Token Index: 484

Text #9

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.4012. Min Act: -0.1700

Data Index: 6923880 (Open Web Text)

Max Activating Token Index: 270

Text #10

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.3939. Min Act: -0.1700

Data Index: 1334873 (Open Web Text)

Max Activating Token Index: 141

Text #11

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.3952. Min Act: -0.1700

Data Index: 3590337 (Open Web Text)

Max Activating Token Index: 451

Text #12

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.3784. Min Act: -0.1700

Data Index: 8789979 (Open Web Text)

Max Activating Token Index: 348

Text #13

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.3694. Min Act: -0.1700

Data Index: 4545772 (Open Web Text)

Max Activating Token Index: 316

Text #14

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.3706. Min Act: -0.1700

Data Index: 6848000 (Open Web Text)

Max Activating Token Index: 285

Text #15

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.3797. Min Act: -0.1700

Data Index: 2069320 (Open Web Text)

Max Activating Token Index: 200

Text #16

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.3684. Min Act: -0.1700

Data Index: 1372731 (Open Web Text)

Max Activating Token Index: 186

Text #17

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.3762. Min Act: -0.1700

Data Index: 7327657 (Open Web Text)

Max Activating Token Index: 76

Text #18

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.3653. Min Act: -0.1700

Data Index: 2263504 (Open Web Text)

Max Activating Token Index: 772

Text #19

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.3483. Min Act: -0.1700

Data Index: 3007066 (Open Web Text)

Max Activating Token Index: 420