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

Dataset: Open Web Text

Neuron 1730 in Layer 0

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: 1.4514. Min Range: -1.4514

Max Act: 1.4514. Min Act: -0.0938

Data Index: 4442309 (Open Web Text)

Max Activating Token Index: 204

Text #1

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.4295. Min Act: -0.0440

Data Index: 3962846 (Open Web Text)

Max Activating Token Index: 437

Text #2

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.4174. Min Act: -0.0934

Data Index: 8427693 (Open Web Text)

Max Activating Token Index: 746

Text #3

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.4251. Min Act: -0.0656

Data Index: 8465223 (Open Web Text)

Max Activating Token Index: 519

Text #4

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.3957. Min Act: -0.0210

Data Index: 700055 (Open Web Text)

Max Activating Token Index: 560

Text #5

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.3899. Min Act: -0.0738

Data Index: 3045028 (Open Web Text)

Max Activating Token Index: 291

Text #6

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.3990. Min Act: -0.0906

Data Index: 2274690 (Open Web Text)

Max Activating Token Index: 653

Text #7

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.3942. Min Act: -0.1002

Data Index: 4510613 (Open Web Text)

Max Activating Token Index: 677

Text #8

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.3860. Min Act: -0.0889

Data Index: 5226309 (Open Web Text)

Max Activating Token Index: 652

Text #9

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.3821. Min Act: -0.0929

Data Index: 3416867 (Open Web Text)

Max Activating Token Index: 325

Text #10

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.3943. Min Act: -0.0488

Data Index: 3703893 (Open Web Text)

Max Activating Token Index: 638

Text #11

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.3852. Min Act: -0.0381

Data Index: 4186110 (Open Web Text)

Max Activating Token Index: 555

Text #12

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.3810. Min Act: -0.0542

Data Index: 4854744 (Open Web Text)

Max Activating Token Index: 456

Text #13

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.3678. Min Act: -0.0671

Data Index: 7527436 (Open Web Text)

Max Activating Token Index: 398

Text #14

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.3789. Min Act: -0.0691

Data Index: 3962845 (Open Web Text)

Max Activating Token Index: 699

Text #15

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.3473. Min Act: -0.1111

Data Index: 6415328 (Open Web Text)

Max Activating Token Index: 484

Text #16

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.3762. Min Act: -0.0796

Data Index: 5326764 (Open Web Text)

Max Activating Token Index: 178

Text #17

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.3630. Min Act: -0.0139

Data Index: 7164195 (Open Web Text)

Max Activating Token Index: 290

Text #18

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.3624. Min Act: -0.1030

Data Index: 3265759 (Open Web Text)

Max Activating Token Index: 469

Text #19

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.3615. Min Act: -0.0616

Data Index: 7201519 (Open Web Text)

Max Activating Token Index: 488