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

Dataset: Open Web Text

Neuron 2986 in Layer 6

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: 4.0511. Min Range: -4.0511

Max Act: 4.0386. Min Act: -0.1700

Data Index: 4496304 (Open Web Text)

Max Activating Token Index: 778

Text #1

Max Range: 4.0511. Min Range: -4.0511

Max Act: 4.0511. Min Act: -0.1700

Data Index: 7936313 (Open Web Text)

Max Activating Token Index: 909

Text #2

Max Range: 4.0511. Min Range: -4.0511

Max Act: 4.0466. Min Act: -0.1700

Data Index: 1259131 (Open Web Text)

Max Activating Token Index: 168

Text #3

Max Range: 4.0511. Min Range: -4.0511

Max Act: 4.0179. Min Act: -0.1700

Data Index: 6151613 (Open Web Text)

Max Activating Token Index: 805

Text #4

Max Range: 4.0511. Min Range: -4.0511

Max Act: 3.9911. Min Act: -0.1700

Data Index: 3957406 (Open Web Text)

Max Activating Token Index: 505

Text #5

Max Range: 4.0511. Min Range: -4.0511

Max Act: 3.9566. Min Act: -0.1700

Data Index: 3696125 (Open Web Text)

Max Activating Token Index: 91

Text #6

Max Range: 4.0511. Min Range: -4.0511

Max Act: 3.9347. Min Act: -0.1700

Data Index: 491699 (Open Web Text)

Max Activating Token Index: 242

Text #7

Max Range: 4.0511. Min Range: -4.0511

Max Act: 3.9622. Min Act: -0.1700

Data Index: 7563922 (Open Web Text)

Max Activating Token Index: 969

Text #8

Max Range: 4.0511. Min Range: -4.0511

Max Act: 3.9303. Min Act: -0.1700

Data Index: 3807553 (Open Web Text)

Max Activating Token Index: 753

Text #9

Max Range: 4.0511. Min Range: -4.0511

Max Act: 3.9331. Min Act: -0.1700

Data Index: 8182982 (Open Web Text)

Max Activating Token Index: 314

Text #10

Max Range: 4.0511. Min Range: -4.0511

Max Act: 3.8793. Min Act: -0.1700

Data Index: 3017933 (Open Web Text)

Max Activating Token Index: 87

Text #11

Max Range: 4.0511. Min Range: -4.0511

Max Act: 3.8843. Min Act: -0.1700

Data Index: 2093167 (Open Web Text)

Max Activating Token Index: 93

Text #12

Max Range: 4.0511. Min Range: -4.0511

Max Act: 3.8777. Min Act: -0.1700

Data Index: 5735518 (Open Web Text)

Max Activating Token Index: 52

Text #13

Max Range: 4.0511. Min Range: -4.0511

Max Act: 3.8762. Min Act: -0.1700

Data Index: 5668779 (Open Web Text)

Max Activating Token Index: 210

Text #14

Max Range: 4.0511. Min Range: -4.0511

Max Act: 3.8863. Min Act: -0.1700

Data Index: 5390372 (Open Web Text)

Max Activating Token Index: 566

Text #15

Max Range: 4.0511. Min Range: -4.0511

Max Act: 3.9023. Min Act: -0.1700

Data Index: 4912683 (Open Web Text)

Max Activating Token Index: 998

Text #16

Max Range: 4.0511. Min Range: -4.0511

Max Act: 3.8962. Min Act: -0.1700

Data Index: 3737055 (Open Web Text)

Max Activating Token Index: 580

Text #17

Max Range: 4.0511. Min Range: -4.0511

Max Act: 3.8596. Min Act: -0.1700

Data Index: 75345 (Open Web Text)

Max Activating Token Index: 459

Text #18

Max Range: 4.0511. Min Range: -4.0511

Max Act: 3.8400. Min Act: -0.1700

Data Index: 4572831 (Open Web Text)

Max Activating Token Index: 935

Text #19

Max Range: 4.0511. Min Range: -4.0511

Max Act: 3.8685. Min Act: -0.1700

Data Index: 1413388 (Open Web Text)

Max Activating Token Index: 755