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

Dataset: Open Web Text

Neuron 1162 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: 4.1286. Min Range: -4.1286

Max Act: 4.1286. Min Act: -0.1700

Data Index: 2324472 (Open Web Text)

Max Activating Token Index: 371

Text #1

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.9842. Min Act: -0.1700

Data Index: 407348 (Open Web Text)

Max Activating Token Index: 66

Text #2

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.9454. Min Act: -0.1700

Data Index: 564282 (Open Web Text)

Max Activating Token Index: 195

Text #3

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.7691. Min Act: -0.1700

Data Index: 6491418 (Open Web Text)

Max Activating Token Index: 762

Text #4

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.7976. Min Act: -0.1700

Data Index: 8005769 (Open Web Text)

Max Activating Token Index: 663

Text #5

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.7783. Min Act: -0.1700

Data Index: 7664472 (Open Web Text)

Max Activating Token Index: 585

Text #6

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.7442. Min Act: -0.1699

Data Index: 5051706 (Open Web Text)

Max Activating Token Index: 818

Text #7

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.7240. Min Act: -0.1700

Data Index: 1923242 (Open Web Text)

Max Activating Token Index: 509

Text #8

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.7318. Min Act: -0.1700

Data Index: 4382860 (Open Web Text)

Max Activating Token Index: 127

Text #9

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.7048. Min Act: -0.1700

Data Index: 6937230 (Open Web Text)

Max Activating Token Index: 1017

Text #10

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.7342. Min Act: -0.1700

Data Index: 949037 (Open Web Text)

Max Activating Token Index: 930

Text #11

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.7211. Min Act: -0.1700

Data Index: 6340083 (Open Web Text)

Max Activating Token Index: 486

Text #12

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.7189. Min Act: -0.1700

Data Index: 5051718 (Open Web Text)

Max Activating Token Index: 573

Text #13

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.6853. Min Act: -0.1700

Data Index: 5842030 (Open Web Text)

Max Activating Token Index: 287

Text #14

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.7103. Min Act: -0.1700

Data Index: 2351598 (Open Web Text)

Max Activating Token Index: 814

Text #15

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.6752. Min Act: -0.1700

Data Index: 911903 (Open Web Text)

Max Activating Token Index: 160

Text #16

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.6637. Min Act: -0.1700

Data Index: 5051709 (Open Web Text)

Max Activating Token Index: 580

Text #17

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.7087. Min Act: -0.1700

Data Index: 3466663 (Open Web Text)

Max Activating Token Index: 842

Text #18

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.6891. Min Act: -0.1700

Data Index: 467867 (Open Web Text)

Max Activating Token Index: 671

Text #19

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.6861. Min Act: -0.1700

Data Index: 4487896 (Open Web Text)

Max Activating Token Index: 486