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

Dataset: Open Web Text

Neuron 2475 in Layer 6

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: 3.4262. Min Range: -3.4262

Max Act: 3.4262. Min Act: -0.1700

Data Index: 6242599 (Open Web Text)

Max Activating Token Index: 581

Text #1

Max Range: 3.4262. Min Range: -3.4262

Max Act: 3.3787. Min Act: -0.1700

Data Index: 7225104 (Open Web Text)

Max Activating Token Index: 874

Text #2

Max Range: 3.4262. Min Range: -3.4262

Max Act: 3.3326. Min Act: -0.1700

Data Index: 5230624 (Open Web Text)

Max Activating Token Index: 530

Text #3

Max Range: 3.4262. Min Range: -3.4262

Max Act: 3.3150. Min Act: -0.1700

Data Index: 4800553 (Open Web Text)

Max Activating Token Index: 393

Text #4

Max Range: 3.4262. Min Range: -3.4262

Max Act: 3.3159. Min Act: -0.1700

Data Index: 8527507 (Open Web Text)

Max Activating Token Index: 216

Text #5

Max Range: 3.4262. Min Range: -3.4262

Max Act: 3.3230. Min Act: -0.1700

Data Index: 7037533 (Open Web Text)

Max Activating Token Index: 250

Text #6

Max Range: 3.4262. Min Range: -3.4262

Max Act: 3.3149. Min Act: -0.1700

Data Index: 3955434 (Open Web Text)

Max Activating Token Index: 64

Text #7

Max Range: 3.4262. Min Range: -3.4262

Max Act: 3.2948. Min Act: -0.1700

Data Index: 1255668 (Open Web Text)

Max Activating Token Index: 314

Text #8

Max Range: 3.4262. Min Range: -3.4262

Max Act: 3.2797. Min Act: -0.1700

Data Index: 2414563 (Open Web Text)

Max Activating Token Index: 329

Text #9

Max Range: 3.4262. Min Range: -3.4262

Max Act: 3.2675. Min Act: -0.1700

Data Index: 5248392 (Open Web Text)

Max Activating Token Index: 196

Text #10

Max Range: 3.4262. Min Range: -3.4262

Max Act: 3.2595. Min Act: -0.1700

Data Index: 3311676 (Open Web Text)

Max Activating Token Index: 670

Text #11

Max Range: 3.4262. Min Range: -3.4262

Max Act: 3.2711. Min Act: -0.1700

Data Index: 2199247 (Open Web Text)

Max Activating Token Index: 609

Text #12

Max Range: 3.4262. Min Range: -3.4262

Max Act: 3.2695. Min Act: -0.1700

Data Index: 3406841 (Open Web Text)

Max Activating Token Index: 596

Text #13

Max Range: 3.4262. Min Range: -3.4262

Max Act: 3.2456. Min Act: -0.1700

Data Index: 8440439 (Open Web Text)

Max Activating Token Index: 689

Text #14

Max Range: 3.4262. Min Range: -3.4262

Max Act: 3.2527. Min Act: -0.1700

Data Index: 3735888 (Open Web Text)

Max Activating Token Index: 939

Text #15

Max Range: 3.4262. Min Range: -3.4262

Max Act: 3.2511. Min Act: -0.1700

Data Index: 6229228 (Open Web Text)

Max Activating Token Index: 1011

Text #16

Max Range: 3.4262. Min Range: -3.4262

Max Act: 3.2291. Min Act: -0.1700

Data Index: 1325669 (Open Web Text)

Max Activating Token Index: 368

Text #17

Max Range: 3.4262. Min Range: -3.4262

Max Act: 3.2352. Min Act: -0.1700

Data Index: 6630208 (Open Web Text)

Max Activating Token Index: 52

Text #18

Max Range: 3.4262. Min Range: -3.4262

Max Act: 3.2081. Min Act: -0.1700

Data Index: 4466990 (Open Web Text)

Max Activating Token Index: 499

Text #19

Max Range: 3.4262. Min Range: -3.4262

Max Act: 3.2396. Min Act: -0.1700

Data Index: 3640108 (Open Web Text)

Max Activating Token Index: 508