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

Dataset: Open Web Text

Neuron 1318 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: 2.9164. Min Range: -2.9164

Max Act: 2.9164. Min Act: -0.1700

Data Index: 6906269 (Open Web Text)

Max Activating Token Index: 698

Text #1

Max Range: 2.9164. Min Range: -2.9164

Max Act: 2.8809. Min Act: -0.1700

Data Index: 13522 (Open Web Text)

Max Activating Token Index: 589

Text #2

Max Range: 2.9164. Min Range: -2.9164

Max Act: 2.8867. Min Act: -0.1700

Data Index: 6405107 (Open Web Text)

Max Activating Token Index: 43

Text #3

Max Range: 2.9164. Min Range: -2.9164

Max Act: 2.8495. Min Act: -0.1700

Data Index: 2173318 (Open Web Text)

Max Activating Token Index: 705

Text #4

Max Range: 2.9164. Min Range: -2.9164

Max Act: 2.8502. Min Act: -0.1700

Data Index: 72846 (Open Web Text)

Max Activating Token Index: 460

Text #5

Max Range: 2.9164. Min Range: -2.9164

Max Act: 2.8674. Min Act: -0.1700

Data Index: 907056 (Open Web Text)

Max Activating Token Index: 764

Text #6

Max Range: 2.9164. Min Range: -2.9164

Max Act: 2.8604. Min Act: -0.1700

Data Index: 898474 (Open Web Text)

Max Activating Token Index: 106

Text #7

Max Range: 2.9164. Min Range: -2.9164

Max Act: 2.8401. Min Act: -0.1700

Data Index: 5604832 (Open Web Text)

Max Activating Token Index: 101

Text #8

Max Range: 2.9164. Min Range: -2.9164

Max Act: 2.8468. Min Act: -0.1700

Data Index: 2705935 (Open Web Text)

Max Activating Token Index: 338

Text #9

Max Range: 2.9164. Min Range: -2.9164

Max Act: 2.8509. Min Act: -0.1700

Data Index: 4444551 (Open Web Text)

Max Activating Token Index: 756

Text #10

Max Range: 2.9164. Min Range: -2.9164

Max Act: 2.8293. Min Act: -0.1700

Data Index: 8744874 (Open Web Text)

Max Activating Token Index: 526

Text #11

Max Range: 2.9164. Min Range: -2.9164

Max Act: 2.8318. Min Act: -0.1700

Data Index: 294021 (Open Web Text)

Max Activating Token Index: 1019

Text #12

Max Range: 2.9164. Min Range: -2.9164

Max Act: 2.8506. Min Act: -0.1700

Data Index: 3725008 (Open Web Text)

Max Activating Token Index: 17

Text #13

Max Range: 2.9164. Min Range: -2.9164

Max Act: 2.8340. Min Act: -0.1700

Data Index: 1564625 (Open Web Text)

Max Activating Token Index: 673

Text #14

Max Range: 2.9164. Min Range: -2.9164

Max Act: 2.8515. Min Act: -0.1700

Data Index: 8617223 (Open Web Text)

Max Activating Token Index: 381

Text #15

Max Range: 2.9164. Min Range: -2.9164

Max Act: 2.8242. Min Act: -0.1700

Data Index: 2216469 (Open Web Text)

Max Activating Token Index: 87

Text #16

Max Range: 2.9164. Min Range: -2.9164

Max Act: 2.8144. Min Act: -0.1700

Data Index: 4270503 (Open Web Text)

Max Activating Token Index: 149

Text #17

Max Range: 2.9164. Min Range: -2.9164

Max Act: 2.8068. Min Act: -0.1700

Data Index: 2575526 (Open Web Text)

Max Activating Token Index: 526

Text #18

Max Range: 2.9164. Min Range: -2.9164

Max Act: 2.7941. Min Act: -0.1700

Data Index: 2561970 (Open Web Text)

Max Activating Token Index: 70

Text #19

Max Range: 2.9164. Min Range: -2.9164

Max Act: 2.8002. Min Act: -0.1700

Data Index: 198715 (Open Web Text)

Max Activating Token Index: 33