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

Dataset: Open Web Text

Neuron 2190 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: 1.5713. Min Range: -1.5713

Max Act: 1.5713. Min Act: -0.1697

Data Index: 2035669 (Open Web Text)

Max Activating Token Index: 59

Text #1

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4857. Min Act: -0.1700

Data Index: 7339135 (Open Web Text)

Max Activating Token Index: 250

Text #2

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4817. Min Act: -0.1697

Data Index: 3786798 (Open Web Text)

Max Activating Token Index: 620

Text #3

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4830. Min Act: -0.1700

Data Index: 7437506 (Open Web Text)

Max Activating Token Index: 632

Text #4

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4760. Min Act: -0.1698

Data Index: 5064406 (Open Web Text)

Max Activating Token Index: 748

Text #5

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4691. Min Act: -0.1700

Data Index: 5575687 (Open Web Text)

Max Activating Token Index: 672

Text #6

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4742. Min Act: -0.1700

Data Index: 977840 (Open Web Text)

Max Activating Token Index: 90

Text #7

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4596. Min Act: -0.1700

Data Index: 6185449 (Open Web Text)

Max Activating Token Index: 881

Text #8

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4570. Min Act: -0.1698

Data Index: 7452854 (Open Web Text)

Max Activating Token Index: 610

Text #9

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4462. Min Act: -0.1677

Data Index: 4267348 (Open Web Text)

Max Activating Token Index: 342

Text #10

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4426. Min Act: -0.1700

Data Index: 5207407 (Open Web Text)

Max Activating Token Index: 26

Text #11

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4503. Min Act: -0.1700

Data Index: 8286036 (Open Web Text)

Max Activating Token Index: 264

Text #12

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4373. Min Act: -0.1700

Data Index: 977839 (Open Web Text)

Max Activating Token Index: 183

Text #13

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4423. Min Act: -0.1700

Data Index: 4279717 (Open Web Text)

Max Activating Token Index: 132

Text #14

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4386. Min Act: -0.1700

Data Index: 6216152 (Open Web Text)

Max Activating Token Index: 288

Text #15

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4332. Min Act: -0.1700

Data Index: 7336832 (Open Web Text)

Max Activating Token Index: 731

Text #16

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4396. Min Act: -0.1700

Data Index: 1164772 (Open Web Text)

Max Activating Token Index: 708

Text #17

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4212. Min Act: -0.1700

Data Index: 7402540 (Open Web Text)

Max Activating Token Index: 935

Text #18

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4357. Min Act: -0.1700

Data Index: 387274 (Open Web Text)

Max Activating Token Index: 68

Text #19

Max Range: 1.5713. Min Range: -1.5713

Max Act: 1.4309. Min Act: -0.1700

Data Index: 2390874 (Open Web Text)

Max Activating Token Index: 329