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

Dataset: Open Web Text

Neuron 584 in Layer 5

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: 2.9437. Min Range: -2.9437

Max Act: 2.9437. Min Act: -0.1700

Data Index: 6538033 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.9437. Min Range: -2.9437

Max Act: 2.8922. Min Act: -0.1700

Data Index: 4308454 (Open Web Text)

Max Activating Token Index: 905

Text #2

Max Range: 2.9437. Min Range: -2.9437

Max Act: 2.7929. Min Act: -0.1700

Data Index: 1587842 (Open Web Text)

Max Activating Token Index: 819

Text #3

Max Range: 2.9437. Min Range: -2.9437

Max Act: 2.6610. Min Act: -0.1700

Data Index: 1595634 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 2.9437. Min Range: -2.9437

Max Act: 2.6900. Min Act: -0.1700

Data Index: 3021744 (Open Web Text)

Max Activating Token Index: 746

Text #5

Max Range: 2.9437. Min Range: -2.9437

Max Act: 2.6555. Min Act: -0.1700

Data Index: 3249493 (Open Web Text)

Max Activating Token Index: 896

Text #6

Max Range: 2.9437. Min Range: -2.9437

Max Act: 2.6535. Min Act: -0.1700

Data Index: 2528268 (Open Web Text)

Max Activating Token Index: 773

Text #7

Max Range: 2.9437. Min Range: -2.9437

Max Act: 2.6892. Min Act: -0.1700

Data Index: 3281835 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 2.9437. Min Range: -2.9437

Max Act: 2.6239. Min Act: -0.1700

Data Index: 3249481 (Open Web Text)

Max Activating Token Index: 955

Text #9

Max Range: 2.9437. Min Range: -2.9437

Max Act: 2.6212. Min Act: -0.1700

Data Index: 1007393 (Open Web Text)

Max Activating Token Index: 775

Text #10

Max Range: 2.9437. Min Range: -2.9437

Max Act: 2.6088. Min Act: -0.1700

Data Index: 6921358 (Open Web Text)

Max Activating Token Index: 424

Text #11

Max Range: 2.9437. Min Range: -2.9437

Max Act: 2.5883. Min Act: -0.1700

Data Index: 7867419 (Open Web Text)

Max Activating Token Index: 957

Text #12

Max Range: 2.9437. Min Range: -2.9437

Max Act: 2.6065. Min Act: -0.1700

Data Index: 1595638 (Open Web Text)

Max Activating Token Index: 957

Text #13

Max Range: 2.9437. Min Range: -2.9437

Max Act: 2.6151. Min Act: -0.1700

Data Index: 1595626 (Open Web Text)

Max Activating Token Index: 851

Text #14

Max Range: 2.9437. Min Range: -2.9437

Max Act: 2.5547. Min Act: -0.1700

Data Index: 1732300 (Open Web Text)

Max Activating Token Index: 651

Text #15

Max Range: 2.9437. Min Range: -2.9437

Max Act: 2.5499. Min Act: -0.1700

Data Index: 5137413 (Open Web Text)

Max Activating Token Index: 269

Text #16

Max Range: 2.9437. Min Range: -2.9437

Max Act: 2.5443. Min Act: -0.1700

Data Index: 6534228 (Open Web Text)

Max Activating Token Index: 888

Text #17

Max Range: 2.9437. Min Range: -2.9437

Max Act: 2.5524. Min Act: -0.1700

Data Index: 4373082 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 2.9437. Min Range: -2.9437

Max Act: 2.5466. Min Act: -0.1700

Data Index: 1595630 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 2.9437. Min Range: -2.9437

Max Act: 2.4968. Min Act: -0.1700

Data Index: 2100877 (Open Web Text)

Max Activating Token Index: 623