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

Dataset: Open Web Text

Neuron 591 in Layer 1

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: 1.6377. Min Range: -1.6377

Max Act: 1.6377. Min Act: -0.1700

Data Index: 3488618 (Open Web Text)

Max Activating Token Index: 286

Text #1

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.6015. Min Act: -0.1700

Data Index: 6655154 (Open Web Text)

Max Activating Token Index: 428

Text #2

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.5934. Min Act: -0.1700

Data Index: 1075490 (Open Web Text)

Max Activating Token Index: 577

Text #3

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.5833. Min Act: -0.1700

Data Index: 3474423 (Open Web Text)

Max Activating Token Index: 694

Text #4

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.5884. Min Act: -0.1700

Data Index: 3424223 (Open Web Text)

Max Activating Token Index: 466

Text #5

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.5802. Min Act: -0.1700

Data Index: 3627064 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.5728. Min Act: -0.1700

Data Index: 2430478 (Open Web Text)

Max Activating Token Index: 822

Text #7

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.5673. Min Act: -0.1700

Data Index: 8037956 (Open Web Text)

Max Activating Token Index: 444

Text #8

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.5653. Min Act: -0.1700

Data Index: 4979265 (Open Web Text)

Max Activating Token Index: 727

Text #9

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.5556. Min Act: -0.1700

Data Index: 1493656 (Open Web Text)

Max Activating Token Index: 490

Text #10

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.5530. Min Act: -0.1700

Data Index: 480615 (Open Web Text)

Max Activating Token Index: 178

Text #11

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.5522. Min Act: -0.1700

Data Index: 5119032 (Open Web Text)

Max Activating Token Index: 242

Text #12

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.5540. Min Act: -0.1670

Data Index: 6187633 (Open Web Text)

Max Activating Token Index: 148

Text #13

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.5487. Min Act: -0.1700

Data Index: 3272603 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.5447. Min Act: -0.1700

Data Index: 4010589 (Open Web Text)

Max Activating Token Index: 954

Text #15

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.5330. Min Act: -0.1698

Data Index: 2179189 (Open Web Text)

Max Activating Token Index: 435

Text #16

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.5401. Min Act: -0.1700

Data Index: 2927621 (Open Web Text)

Max Activating Token Index: 664

Text #17

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.5464. Min Act: -0.1700

Data Index: 5419618 (Open Web Text)

Max Activating Token Index: 703

Text #18

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.5530. Min Act: -0.1700

Data Index: 5792071 (Open Web Text)

Max Activating Token Index: 810

Text #19

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.5371. Min Act: -0.1700

Data Index: 4276399 (Open Web Text)

Max Activating Token Index: 446