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

Dataset: Open Web Text

Neuron 938 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: 3.2816. Min Range: -3.2816

Max Act: 3.2816. Min Act: -0.1700

Data Index: 493819 (Open Web Text)

Max Activating Token Index: 17

Text #1

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.2644. Min Act: -0.1700

Data Index: 2892996 (Open Web Text)

Max Activating Token Index: 367

Text #2

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.2570. Min Act: -0.1700

Data Index: 4579040 (Open Web Text)

Max Activating Token Index: 810

Text #3

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.2301. Min Act: -0.1700

Data Index: 6051723 (Open Web Text)

Max Activating Token Index: 585

Text #4

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.2026. Min Act: -0.1700

Data Index: 8390230 (Open Web Text)

Max Activating Token Index: 483

Text #5

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.2043. Min Act: -0.1700

Data Index: 598892 (Open Web Text)

Max Activating Token Index: 740

Text #6

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.1774. Min Act: -0.1700

Data Index: 7975732 (Open Web Text)

Max Activating Token Index: 630

Text #7

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.1915. Min Act: -0.1700

Data Index: 3813543 (Open Web Text)

Max Activating Token Index: 616

Text #8

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.1624. Min Act: -0.1700

Data Index: 7840846 (Open Web Text)

Max Activating Token Index: 507

Text #9

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.1538. Min Act: -0.1700

Data Index: 5741445 (Open Web Text)

Max Activating Token Index: 693

Text #10

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.1587. Min Act: -0.1700

Data Index: 444929 (Open Web Text)

Max Activating Token Index: 280

Text #11

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.1438. Min Act: -0.1700

Data Index: 159604 (Open Web Text)

Max Activating Token Index: 214

Text #12

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.1518. Min Act: -0.1700

Data Index: 7783336 (Open Web Text)

Max Activating Token Index: 761

Text #13

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.1505. Min Act: -0.1700

Data Index: 3132844 (Open Web Text)

Max Activating Token Index: 348

Text #14

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.1398. Min Act: -0.1700

Data Index: 2296954 (Open Web Text)

Max Activating Token Index: 623

Text #15

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.1639. Min Act: -0.1700

Data Index: 4259134 (Open Web Text)

Max Activating Token Index: 690

Text #16

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.1281. Min Act: -0.1700

Data Index: 4775451 (Open Web Text)

Max Activating Token Index: 444

Text #17

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.1162. Min Act: -0.1700

Data Index: 7637831 (Open Web Text)

Max Activating Token Index: 456

Text #18

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.0969. Min Act: -0.1700

Data Index: 4639282 (Open Web Text)

Max Activating Token Index: 34

Text #19

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.0934. Min Act: -0.1700

Data Index: 2749370 (Open Web Text)

Max Activating Token Index: 191