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

Dataset: Open Web Text

Neuron 1400 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: 2.1865. Min Range: -2.1865

Max Act: 2.1865. Min Act: -0.1700

Data Index: 4633576 (Open Web Text)

Max Activating Token Index: 529

Text #1

Max Range: 2.1865. Min Range: -2.1865

Max Act: 2.1791. Min Act: -0.1700

Data Index: 627376 (Open Web Text)

Max Activating Token Index: 985

Text #2

Max Range: 2.1865. Min Range: -2.1865

Max Act: 2.1532. Min Act: -0.1700

Data Index: 5414865 (Open Web Text)

Max Activating Token Index: 619

Text #3

Max Range: 2.1865. Min Range: -2.1865

Max Act: 2.1536. Min Act: -0.1700

Data Index: 3653318 (Open Web Text)

Max Activating Token Index: 304

Text #4

Max Range: 2.1865. Min Range: -2.1865

Max Act: 2.1520. Min Act: -0.1700

Data Index: 6963267 (Open Web Text)

Max Activating Token Index: 447

Text #5

Max Range: 2.1865. Min Range: -2.1865

Max Act: 2.1274. Min Act: -0.1700

Data Index: 5900137 (Open Web Text)

Max Activating Token Index: 1017

Text #6

Max Range: 2.1865. Min Range: -2.1865

Max Act: 2.0894. Min Act: -0.1696

Data Index: 6243942 (Open Web Text)

Max Activating Token Index: 1017

Text #7

Max Range: 2.1865. Min Range: -2.1865

Max Act: 2.0993. Min Act: -0.1700

Data Index: 4931519 (Open Web Text)

Max Activating Token Index: 594

Text #8

Max Range: 2.1865. Min Range: -2.1865

Max Act: 2.0774. Min Act: -0.1700

Data Index: 8660471 (Open Web Text)

Max Activating Token Index: 671

Text #9

Max Range: 2.1865. Min Range: -2.1865

Max Act: 2.0814. Min Act: -0.1700

Data Index: 170816 (Open Web Text)

Max Activating Token Index: 648

Text #10

Max Range: 2.1865. Min Range: -2.1865

Max Act: 2.0785. Min Act: -0.1700

Data Index: 4370274 (Open Web Text)

Max Activating Token Index: 177

Text #11

Max Range: 2.1865. Min Range: -2.1865

Max Act: 2.0726. Min Act: -0.1700

Data Index: 3733 (Open Web Text)

Max Activating Token Index: 460

Text #12

Max Range: 2.1865. Min Range: -2.1865

Max Act: 2.0771. Min Act: -0.1700

Data Index: 162421 (Open Web Text)

Max Activating Token Index: 374

Text #13

Max Range: 2.1865. Min Range: -2.1865

Max Act: 2.0892. Min Act: -0.1700

Data Index: 7797111 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 2.1865. Min Range: -2.1865

Max Act: 2.0716. Min Act: -0.1700

Data Index: 8477638 (Open Web Text)

Max Activating Token Index: 625

Text #15

Max Range: 2.1865. Min Range: -2.1865

Max Act: 2.0612. Min Act: -0.1700

Data Index: 8240580 (Open Web Text)

Max Activating Token Index: 599

Text #16

Max Range: 2.1865. Min Range: -2.1865

Max Act: 2.0739. Min Act: -0.1700

Data Index: 8150543 (Open Web Text)

Max Activating Token Index: 1021

Text #17

Max Range: 2.1865. Min Range: -2.1865

Max Act: 2.0705. Min Act: -0.1700

Data Index: 7664739 (Open Web Text)

Max Activating Token Index: 85

Text #18

Max Range: 2.1865. Min Range: -2.1865

Max Act: 2.0507. Min Act: -0.1700

Data Index: 7215207 (Open Web Text)

Max Activating Token Index: 521

Text #19

Max Range: 2.1865. Min Range: -2.1865

Max Act: 2.0701. Min Act: -0.1700

Data Index: 6641607 (Open Web Text)

Max Activating Token Index: 259