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

Dataset: Open Web Text

Neuron 2881 in Layer 3

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: 4.4425. Min Range: -4.4425

Max Act: 4.4425. Min Act: -0.1700

Data Index: 495377 (Open Web Text)

Max Activating Token Index: 724

Text #1

Max Range: 4.4425. Min Range: -4.4425

Max Act: 4.3070. Min Act: -0.1700

Data Index: 4673037 (Open Web Text)

Max Activating Token Index: 773

Text #2

Max Range: 4.4425. Min Range: -4.4425

Max Act: 4.3138. Min Act: -0.1700

Data Index: 836095 (Open Web Text)

Max Activating Token Index: 676

Text #3

Max Range: 4.4425. Min Range: -4.4425

Max Act: 4.2645. Min Act: -0.1700

Data Index: 2831975 (Open Web Text)

Max Activating Token Index: 473

Text #4

Max Range: 4.4425. Min Range: -4.4425

Max Act: 4.2586. Min Act: -0.1700

Data Index: 300338 (Open Web Text)

Max Activating Token Index: 619

Text #5

Max Range: 4.4425. Min Range: -4.4425

Max Act: 4.2929. Min Act: -0.1700

Data Index: 5039920 (Open Web Text)

Max Activating Token Index: 470

Text #6

Max Range: 4.4425. Min Range: -4.4425

Max Act: 4.2744. Min Act: -0.1700

Data Index: 3345856 (Open Web Text)

Max Activating Token Index: 67

Text #7

Max Range: 4.4425. Min Range: -4.4425

Max Act: 4.2756. Min Act: -0.1700

Data Index: 2241505 (Open Web Text)

Max Activating Token Index: 812

Text #8

Max Range: 4.4425. Min Range: -4.4425

Max Act: 4.2952. Min Act: -0.1700

Data Index: 6398261 (Open Web Text)

Max Activating Token Index: 379

Text #9

Max Range: 4.4425. Min Range: -4.4425

Max Act: 4.2815. Min Act: -0.1700

Data Index: 769963 (Open Web Text)

Max Activating Token Index: 349

Text #10

Max Range: 4.4425. Min Range: -4.4425

Max Act: 4.2518. Min Act: -0.1700

Data Index: 2153021 (Open Web Text)

Max Activating Token Index: 694

Text #11

Max Range: 4.4425. Min Range: -4.4425

Max Act: 4.2513. Min Act: -0.1700

Data Index: 3903672 (Open Web Text)

Max Activating Token Index: 808

Text #12

Max Range: 4.4425. Min Range: -4.4425

Max Act: 4.2604. Min Act: -0.1700

Data Index: 8006166 (Open Web Text)

Max Activating Token Index: 297

Text #13

Max Range: 4.4425. Min Range: -4.4425

Max Act: 4.2549. Min Act: -0.1700

Data Index: 7376739 (Open Web Text)

Max Activating Token Index: 371

Text #14

Max Range: 4.4425. Min Range: -4.4425

Max Act: 4.2541. Min Act: -0.1700

Data Index: 437413 (Open Web Text)

Max Activating Token Index: 378

Text #15

Max Range: 4.4425. Min Range: -4.4425

Max Act: 4.2662. Min Act: -0.1700

Data Index: 4622843 (Open Web Text)

Max Activating Token Index: 671

Text #16

Max Range: 4.4425. Min Range: -4.4425

Max Act: 4.2539. Min Act: -0.1700

Data Index: 6053808 (Open Web Text)

Max Activating Token Index: 91

Text #17

Max Range: 4.4425. Min Range: -4.4425

Max Act: 4.2362. Min Act: -0.1700

Data Index: 5042494 (Open Web Text)

Max Activating Token Index: 282

Text #18

Max Range: 4.4425. Min Range: -4.4425

Max Act: 4.2300. Min Act: -0.1700

Data Index: 2665094 (Open Web Text)

Max Activating Token Index: 198

Text #19

Max Range: 4.4425. Min Range: -4.4425

Max Act: 4.2440. Min Act: -0.1700

Data Index: 2615646 (Open Web Text)

Max Activating Token Index: 614