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

Dataset: Open Web Text

Neuron 640 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: 4.1721. Min Range: -4.1721

Max Act: 4.1721. Min Act: -0.1700

Data Index: 1201068 (Open Web Text)

Max Activating Token Index: 400

Text #1

Max Range: 4.1721. Min Range: -4.1721

Max Act: 4.0894. Min Act: -0.1700

Data Index: 2801479 (Open Web Text)

Max Activating Token Index: 184

Text #2

Max Range: 4.1721. Min Range: -4.1721

Max Act: 4.0700. Min Act: -0.1700

Data Index: 7381689 (Open Web Text)

Max Activating Token Index: 646

Text #3

Max Range: 4.1721. Min Range: -4.1721

Max Act: 4.0358. Min Act: -0.1700

Data Index: 5842027 (Open Web Text)

Max Activating Token Index: 208

Text #4

Max Range: 4.1721. Min Range: -4.1721

Max Act: 3.9878. Min Act: -0.1700

Data Index: 7553807 (Open Web Text)

Max Activating Token Index: 582

Text #5

Max Range: 4.1721. Min Range: -4.1721

Max Act: 4.0290. Min Act: -0.1700

Data Index: 6932118 (Open Web Text)

Max Activating Token Index: 1006

Text #6

Max Range: 4.1721. Min Range: -4.1721

Max Act: 4.0281. Min Act: -0.1700

Data Index: 8654147 (Open Web Text)

Max Activating Token Index: 78

Text #7

Max Range: 4.1721. Min Range: -4.1721

Max Act: 3.9895. Min Act: -0.1700

Data Index: 3621938 (Open Web Text)

Max Activating Token Index: 524

Text #8

Max Range: 4.1721. Min Range: -4.1721

Max Act: 3.9916. Min Act: -0.1700

Data Index: 2180237 (Open Web Text)

Max Activating Token Index: 740

Text #9

Max Range: 4.1721. Min Range: -4.1721

Max Act: 3.9843. Min Act: -0.1700

Data Index: 2495672 (Open Web Text)

Max Activating Token Index: 564

Text #10

Max Range: 4.1721. Min Range: -4.1721

Max Act: 4.0229. Min Act: -0.1700

Data Index: 1800261 (Open Web Text)

Max Activating Token Index: 539

Text #11

Max Range: 4.1721. Min Range: -4.1721

Max Act: 4.0009. Min Act: -0.1700

Data Index: 2137606 (Open Web Text)

Max Activating Token Index: 339

Text #12

Max Range: 4.1721. Min Range: -4.1721

Max Act: 3.9614. Min Act: -0.1700

Data Index: 240025 (Open Web Text)

Max Activating Token Index: 536

Text #13

Max Range: 4.1721. Min Range: -4.1721

Max Act: 3.9206. Min Act: -0.1700

Data Index: 5766457 (Open Web Text)

Max Activating Token Index: 415

Text #14

Max Range: 4.1721. Min Range: -4.1721

Max Act: 3.9168. Min Act: -0.1700

Data Index: 746586 (Open Web Text)

Max Activating Token Index: 606

Text #15

Max Range: 4.1721. Min Range: -4.1721

Max Act: 3.9062. Min Act: -0.1700

Data Index: 6361464 (Open Web Text)

Max Activating Token Index: 413

Text #16

Max Range: 4.1721. Min Range: -4.1721

Max Act: 3.9273. Min Act: -0.1700

Data Index: 5220467 (Open Web Text)

Max Activating Token Index: 950

Text #17

Max Range: 4.1721. Min Range: -4.1721

Max Act: 3.9177. Min Act: -0.1700

Data Index: 4557520 (Open Web Text)

Max Activating Token Index: 451

Text #18

Max Range: 4.1721. Min Range: -4.1721

Max Act: 3.9453. Min Act: -0.1700

Data Index: 476629 (Open Web Text)

Max Activating Token Index: 593

Text #19

Max Range: 4.1721. Min Range: -4.1721

Max Act: 3.9126. Min Act: -0.1700

Data Index: 64137 (Open Web Text)

Max Activating Token Index: 592