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

Dataset: Open Web Text

Neuron 958 in Layer 1

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: 1.5943. Min Range: -1.5943

Max Act: 1.5829. Min Act: -0.1700

Data Index: 4390159 (Open Web Text)

Max Activating Token Index: 497

Text #1

Max Range: 1.5943. Min Range: -1.5943

Max Act: 1.5943. Min Act: -0.1700

Data Index: 2487200 (Open Web Text)

Max Activating Token Index: 677

Text #2

Max Range: 1.5943. Min Range: -1.5943

Max Act: 1.5733. Min Act: -0.1700

Data Index: 6233028 (Open Web Text)

Max Activating Token Index: 497

Text #3

Max Range: 1.5943. Min Range: -1.5943

Max Act: 1.5705. Min Act: -0.1700

Data Index: 2325479 (Open Web Text)

Max Activating Token Index: 450

Text #4

Max Range: 1.5943. Min Range: -1.5943

Max Act: 1.5630. Min Act: -0.1700

Data Index: 4065017 (Open Web Text)

Max Activating Token Index: 658

Text #5

Max Range: 1.5943. Min Range: -1.5943

Max Act: 1.5614. Min Act: -0.1700

Data Index: 1981459 (Open Web Text)

Max Activating Token Index: 478

Text #6

Max Range: 1.5943. Min Range: -1.5943

Max Act: 1.5557. Min Act: -0.1700

Data Index: 3132236 (Open Web Text)

Max Activating Token Index: 490

Text #7

Max Range: 1.5943. Min Range: -1.5943

Max Act: 1.5540. Min Act: -0.1700

Data Index: 4419029 (Open Web Text)

Max Activating Token Index: 179

Text #8

Max Range: 1.5943. Min Range: -1.5943

Max Act: 1.5447. Min Act: -0.1700

Data Index: 6719532 (Open Web Text)

Max Activating Token Index: 548

Text #9

Max Range: 1.5943. Min Range: -1.5943

Max Act: 1.5455. Min Act: -0.1700

Data Index: 1970096 (Open Web Text)

Max Activating Token Index: 125

Text #10

Max Range: 1.5943. Min Range: -1.5943

Max Act: 1.5503. Min Act: -0.1700

Data Index: 1191832 (Open Web Text)

Max Activating Token Index: 548

Text #11

Max Range: 1.5943. Min Range: -1.5943

Max Act: 1.5415. Min Act: -0.1700

Data Index: 1496680 (Open Web Text)

Max Activating Token Index: 920

Text #12

Max Range: 1.5943. Min Range: -1.5943

Max Act: 1.5391. Min Act: -0.1699

Data Index: 63194 (Open Web Text)

Max Activating Token Index: 630

Text #13

Max Range: 1.5943. Min Range: -1.5943

Max Act: 1.5453. Min Act: -0.1700

Data Index: 3321728 (Open Web Text)

Max Activating Token Index: 312

Text #14

Max Range: 1.5943. Min Range: -1.5943

Max Act: 1.5396. Min Act: -0.1700

Data Index: 8750899 (Open Web Text)

Max Activating Token Index: 151

Text #15

Max Range: 1.5943. Min Range: -1.5943

Max Act: 1.5430. Min Act: -0.1700

Data Index: 8190188 (Open Web Text)

Max Activating Token Index: 103

Text #16

Max Range: 1.5943. Min Range: -1.5943

Max Act: 1.5392. Min Act: -0.1700

Data Index: 7859880 (Open Web Text)

Max Activating Token Index: 363

Text #17

Max Range: 1.5943. Min Range: -1.5943

Max Act: 1.5315. Min Act: -0.1700

Data Index: 6356597 (Open Web Text)

Max Activating Token Index: 713

Text #18

Max Range: 1.5943. Min Range: -1.5943

Max Act: 1.5325. Min Act: -0.1700

Data Index: 594588 (Open Web Text)

Max Activating Token Index: 607

Text #19

Max Range: 1.5943. Min Range: -1.5943

Max Act: 1.5354. Min Act: -0.1700

Data Index: 3603969 (Open Web Text)

Max Activating Token Index: 313