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

Dataset: Open Web Text

Neuron 622 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: 4.1034. Min Range: -4.1034

Max Act: 4.1034. Min Act: -0.1700

Data Index: 4001570 (Open Web Text)

Max Activating Token Index: 825

Text #1

Max Range: 4.1034. Min Range: -4.1034

Max Act: 3.9988. Min Act: -0.1700

Data Index: 8435717 (Open Web Text)

Max Activating Token Index: 860

Text #2

Max Range: 4.1034. Min Range: -4.1034

Max Act: 4.0065. Min Act: -0.1700

Data Index: 5011116 (Open Web Text)

Max Activating Token Index: 884

Text #3

Max Range: 4.1034. Min Range: -4.1034

Max Act: 3.9190. Min Act: -0.1700

Data Index: 2145580 (Open Web Text)

Max Activating Token Index: 678

Text #4

Max Range: 4.1034. Min Range: -4.1034

Max Act: 3.9253. Min Act: -0.1700

Data Index: 7542871 (Open Web Text)

Max Activating Token Index: 602

Text #5

Max Range: 4.1034. Min Range: -4.1034

Max Act: 3.8757. Min Act: -0.1700

Data Index: 2592557 (Open Web Text)

Max Activating Token Index: 116

Text #6

Max Range: 4.1034. Min Range: -4.1034

Max Act: 3.9342. Min Act: -0.1700

Data Index: 2698604 (Open Web Text)

Max Activating Token Index: 841

Text #7

Max Range: 4.1034. Min Range: -4.1034

Max Act: 3.8962. Min Act: -0.1700

Data Index: 5063131 (Open Web Text)

Max Activating Token Index: 321

Text #8

Max Range: 4.1034. Min Range: -4.1034

Max Act: 3.8932. Min Act: -0.1700

Data Index: 8096063 (Open Web Text)

Max Activating Token Index: 151

Text #9

Max Range: 4.1034. Min Range: -4.1034

Max Act: 3.8478. Min Act: -0.1700

Data Index: 5031634 (Open Web Text)

Max Activating Token Index: 627

Text #10

Max Range: 4.1034. Min Range: -4.1034

Max Act: 3.8698. Min Act: -0.1700

Data Index: 8500415 (Open Web Text)

Max Activating Token Index: 625

Text #11

Max Range: 4.1034. Min Range: -4.1034

Max Act: 3.8457. Min Act: -0.1700

Data Index: 1844776 (Open Web Text)

Max Activating Token Index: 918

Text #12

Max Range: 4.1034. Min Range: -4.1034

Max Act: 3.8366. Min Act: -0.1700

Data Index: 3116079 (Open Web Text)

Max Activating Token Index: 293

Text #13

Max Range: 4.1034. Min Range: -4.1034

Max Act: 3.8337. Min Act: -0.1700

Data Index: 5980655 (Open Web Text)

Max Activating Token Index: 867

Text #14

Max Range: 4.1034. Min Range: -4.1034

Max Act: 3.8339. Min Act: -0.1700

Data Index: 754415 (Open Web Text)

Max Activating Token Index: 773

Text #15

Max Range: 4.1034. Min Range: -4.1034

Max Act: 3.8278. Min Act: -0.1700

Data Index: 3174443 (Open Web Text)

Max Activating Token Index: 991

Text #16

Max Range: 4.1034. Min Range: -4.1034

Max Act: 3.8618. Min Act: -0.1700

Data Index: 375920 (Open Web Text)

Max Activating Token Index: 242

Text #17

Max Range: 4.1034. Min Range: -4.1034

Max Act: 3.8294. Min Act: -0.1700

Data Index: 207901 (Open Web Text)

Max Activating Token Index: 893

Text #18

Max Range: 4.1034. Min Range: -4.1034

Max Act: 3.8645. Min Act: -0.1700

Data Index: 6330017 (Open Web Text)

Max Activating Token Index: 740

Text #19

Max Range: 4.1034. Min Range: -4.1034

Max Act: 3.8355. Min Act: -0.1700

Data Index: 3047211 (Open Web Text)

Max Activating Token Index: 949