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

Dataset: Open Web Text

Neuron 577 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: 4.2400. Min Range: -4.2400

Max Act: 4.2400. Min Act: -0.1700

Data Index: 546658 (Open Web Text)

Max Activating Token Index: 452

Text #1

Max Range: 4.2400. Min Range: -4.2400

Max Act: 4.1474. Min Act: -0.1700

Data Index: 6782677 (Open Web Text)

Max Activating Token Index: 416

Text #2

Max Range: 4.2400. Min Range: -4.2400

Max Act: 4.0990. Min Act: -0.1700

Data Index: 4879057 (Open Web Text)

Max Activating Token Index: 980

Text #3

Max Range: 4.2400. Min Range: -4.2400

Max Act: 4.0380. Min Act: -0.1700

Data Index: 6663941 (Open Web Text)

Max Activating Token Index: 963

Text #4

Max Range: 4.2400. Min Range: -4.2400

Max Act: 4.0155. Min Act: -0.1700

Data Index: 599679 (Open Web Text)

Max Activating Token Index: 347

Text #5

Max Range: 4.2400. Min Range: -4.2400

Max Act: 4.0299. Min Act: -0.1700

Data Index: 5255636 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 4.2400. Min Range: -4.2400

Max Act: 3.9976. Min Act: -0.1700

Data Index: 8491018 (Open Web Text)

Max Activating Token Index: 326

Text #7

Max Range: 4.2400. Min Range: -4.2400

Max Act: 4.0214. Min Act: -0.1700

Data Index: 7729253 (Open Web Text)

Max Activating Token Index: 846

Text #8

Max Range: 4.2400. Min Range: -4.2400

Max Act: 3.9966. Min Act: -0.1700

Data Index: 1875797 (Open Web Text)

Max Activating Token Index: 647

Text #9

Max Range: 4.2400. Min Range: -4.2400

Max Act: 3.9579. Min Act: -0.1700

Data Index: 1515133 (Open Web Text)

Max Activating Token Index: 997

Text #10

Max Range: 4.2400. Min Range: -4.2400

Max Act: 4.0060. Min Act: -0.1700

Data Index: 5089867 (Open Web Text)

Max Activating Token Index: 736

Text #11

Max Range: 4.2400. Min Range: -4.2400

Max Act: 3.9943. Min Act: -0.1700

Data Index: 2831016 (Open Web Text)

Max Activating Token Index: 815

Text #12

Max Range: 4.2400. Min Range: -4.2400

Max Act: 3.9242. Min Act: -0.1700

Data Index: 4494646 (Open Web Text)

Max Activating Token Index: 380

Text #13

Max Range: 4.2400. Min Range: -4.2400

Max Act: 3.9728. Min Act: -0.1700

Data Index: 738815 (Open Web Text)

Max Activating Token Index: 583

Text #14

Max Range: 4.2400. Min Range: -4.2400

Max Act: 3.9667. Min Act: -0.1700

Data Index: 5483586 (Open Web Text)

Max Activating Token Index: 57

Text #15

Max Range: 4.2400. Min Range: -4.2400

Max Act: 3.9892. Min Act: -0.1700

Data Index: 3437540 (Open Web Text)

Max Activating Token Index: 649

Text #16

Max Range: 4.2400. Min Range: -4.2400

Max Act: 4.0021. Min Act: -0.1700

Data Index: 2790630 (Open Web Text)

Max Activating Token Index: 925

Text #17

Max Range: 4.2400. Min Range: -4.2400

Max Act: 3.9567. Min Act: -0.1700

Data Index: 143068 (Open Web Text)

Max Activating Token Index: 554

Text #18

Max Range: 4.2400. Min Range: -4.2400

Max Act: 3.9398. Min Act: -0.1700

Data Index: 4316966 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.2400. Min Range: -4.2400

Max Act: 3.9587. Min Act: -0.1700

Data Index: 3880263 (Open Web Text)

Max Activating Token Index: 3