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

Dataset: Open Web Text

Neuron 20 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: 4.3651. Min Range: -4.3651

Max Act: 4.3651. Min Act: -0.1700

Data Index: 2172628 (Open Web Text)

Max Activating Token Index: 475

Text #1

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.2982. Min Act: -0.1700

Data Index: 8649121 (Open Web Text)

Max Activating Token Index: 584

Text #2

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.3076. Min Act: -0.1700

Data Index: 6315118 (Open Web Text)

Max Activating Token Index: 15

Text #3

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.3046. Min Act: -0.1700

Data Index: 2613604 (Open Web Text)

Max Activating Token Index: 859

Text #4

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.3017. Min Act: -0.1700

Data Index: 512747 (Open Web Text)

Max Activating Token Index: 727

Text #5

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.3104. Min Act: -0.1700

Data Index: 5143897 (Open Web Text)

Max Activating Token Index: 544

Text #6

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.2608. Min Act: -0.1700

Data Index: 6558393 (Open Web Text)

Max Activating Token Index: 911

Text #7

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.2628. Min Act: -0.1700

Data Index: 7040658 (Open Web Text)

Max Activating Token Index: 891

Text #8

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.2683. Min Act: -0.1700

Data Index: 7005762 (Open Web Text)

Max Activating Token Index: 432

Text #9

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.2491. Min Act: -0.1700

Data Index: 6953172 (Open Web Text)

Max Activating Token Index: 1004

Text #10

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.2549. Min Act: -0.1700

Data Index: 352466 (Open Web Text)

Max Activating Token Index: 536

Text #11

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.2595. Min Act: -0.1700

Data Index: 1356910 (Open Web Text)

Max Activating Token Index: 541

Text #12

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.2416. Min Act: -0.1700

Data Index: 4211158 (Open Web Text)

Max Activating Token Index: 107

Text #13

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.2426. Min Act: -0.1700

Data Index: 8689455 (Open Web Text)

Max Activating Token Index: 175

Text #14

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.2593. Min Act: -0.1700

Data Index: 724245 (Open Web Text)

Max Activating Token Index: 407

Text #15

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.2314. Min Act: -0.1700

Data Index: 7522400 (Open Web Text)

Max Activating Token Index: 606

Text #16

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.2054. Min Act: -0.1700

Data Index: 480537 (Open Web Text)

Max Activating Token Index: 661

Text #17

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.2647. Min Act: -0.1700

Data Index: 5317526 (Open Web Text)

Max Activating Token Index: 532

Text #18

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.2159. Min Act: -0.1700

Data Index: 1728783 (Open Web Text)

Max Activating Token Index: 440

Text #19

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.2108. Min Act: -0.1700

Data Index: 6549373 (Open Web Text)

Max Activating Token Index: 580