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

Dataset: Open Web Text

Neuron 1194 in Layer 3

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: 4.0809. Min Range: -4.0809

Max Act: 4.0809. Min Act: -0.1700

Data Index: 5301746 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 4.0809. Min Range: -4.0809

Max Act: 4.0269. Min Act: -0.1700

Data Index: 7060707 (Open Web Text)

Max Activating Token Index: 413

Text #2

Max Range: 4.0809. Min Range: -4.0809

Max Act: 4.0336. Min Act: -0.1700

Data Index: 7459396 (Open Web Text)

Max Activating Token Index: 463

Text #3

Max Range: 4.0809. Min Range: -4.0809

Max Act: 4.0472. Min Act: -0.1700

Data Index: 7506708 (Open Web Text)

Max Activating Token Index: 127

Text #4

Max Range: 4.0809. Min Range: -4.0809

Max Act: 4.0380. Min Act: -0.1700

Data Index: 5812797 (Open Web Text)

Max Activating Token Index: 50

Text #5

Max Range: 4.0809. Min Range: -4.0809

Max Act: 4.0133. Min Act: -0.1700

Data Index: 1842772 (Open Web Text)

Max Activating Token Index: 46

Text #6

Max Range: 4.0809. Min Range: -4.0809

Max Act: 4.0042. Min Act: -0.1700

Data Index: 2369693 (Open Web Text)

Max Activating Token Index: 497

Text #7

Max Range: 4.0809. Min Range: -4.0809

Max Act: 4.0278. Min Act: -0.1700

Data Index: 287753 (Open Web Text)

Max Activating Token Index: 961

Text #8

Max Range: 4.0809. Min Range: -4.0809

Max Act: 4.0169. Min Act: -0.1700

Data Index: 8273025 (Open Web Text)

Max Activating Token Index: 90

Text #9

Max Range: 4.0809. Min Range: -4.0809

Max Act: 4.0027. Min Act: -0.1700

Data Index: 8743137 (Open Web Text)

Max Activating Token Index: 487

Text #10

Max Range: 4.0809. Min Range: -4.0809

Max Act: 3.9712. Min Act: -0.1700

Data Index: 5969287 (Open Web Text)

Max Activating Token Index: 698

Text #11

Max Range: 4.0809. Min Range: -4.0809

Max Act: 3.9708. Min Act: -0.1700

Data Index: 7060700 (Open Web Text)

Max Activating Token Index: 493

Text #12

Max Range: 4.0809. Min Range: -4.0809

Max Act: 3.9877. Min Act: -0.1700

Data Index: 3109123 (Open Web Text)

Max Activating Token Index: 122

Text #13

Max Range: 4.0809. Min Range: -4.0809

Max Act: 3.9636. Min Act: -0.1700

Data Index: 4245410 (Open Web Text)

Max Activating Token Index: 675

Text #14

Max Range: 4.0809. Min Range: -4.0809

Max Act: 3.9418. Min Act: -0.1700

Data Index: 2369698 (Open Web Text)

Max Activating Token Index: 294

Text #15

Max Range: 4.0809. Min Range: -4.0809

Max Act: 3.9427. Min Act: -0.1700

Data Index: 2503700 (Open Web Text)

Max Activating Token Index: 189

Text #16

Max Range: 4.0809. Min Range: -4.0809

Max Act: 3.9920. Min Act: -0.1700

Data Index: 2486899 (Open Web Text)

Max Activating Token Index: 397

Text #17

Max Range: 4.0809. Min Range: -4.0809

Max Act: 3.9366. Min Act: -0.1700

Data Index: 4384138 (Open Web Text)

Max Activating Token Index: 304

Text #18

Max Range: 4.0809. Min Range: -4.0809

Max Act: 3.9350. Min Act: -0.1700

Data Index: 4386388 (Open Web Text)

Max Activating Token Index: 540

Text #19

Max Range: 4.0809. Min Range: -4.0809

Max Act: 3.9453. Min Act: -0.1700

Data Index: 6162049 (Open Web Text)

Max Activating Token Index: 529