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

Dataset: Open Web Text

Neuron 1284 in Layer 2

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: 2.7268. Min Range: -2.7268

Max Act: 2.7268. Min Act: -0.1700

Data Index: 1649452 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.7268. Min Range: -2.7268

Max Act: 2.6583. Min Act: -0.1700

Data Index: 4739656 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.7268. Min Range: -2.7268

Max Act: 2.6653. Min Act: -0.1700

Data Index: 7419548 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.7268. Min Range: -2.7268

Max Act: 2.6261. Min Act: -0.1700

Data Index: 7391116 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 2.7268. Min Range: -2.7268

Max Act: 2.5961. Min Act: -0.1700

Data Index: 4946259 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.7268. Min Range: -2.7268

Max Act: 2.6016. Min Act: -0.1700

Data Index: 3269021 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 2.7268. Min Range: -2.7268

Max Act: 2.6070. Min Act: -0.1700

Data Index: 608968 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 2.7268. Min Range: -2.7268

Max Act: 2.5713. Min Act: -0.1700

Data Index: 7675416 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 2.7268. Min Range: -2.7268

Max Act: 2.5765. Min Act: -0.1700

Data Index: 5358074 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 2.7268. Min Range: -2.7268

Max Act: 2.6009. Min Act: -0.1700

Data Index: 1403861 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 2.7268. Min Range: -2.7268

Max Act: 2.5601. Min Act: -0.1700

Data Index: 8662806 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 2.7268. Min Range: -2.7268

Max Act: 2.5446. Min Act: -0.1700

Data Index: 2115056 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 2.7268. Min Range: -2.7268

Max Act: 2.5512. Min Act: -0.1700

Data Index: 4924896 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 2.7268. Min Range: -2.7268

Max Act: 2.5309. Min Act: -0.1700

Data Index: 8767190 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 2.7268. Min Range: -2.7268

Max Act: 2.5404. Min Act: -0.1700

Data Index: 4795861 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 2.7268. Min Range: -2.7268

Max Act: 2.5035. Min Act: -0.1700

Data Index: 130758 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 2.7268. Min Range: -2.7268

Max Act: 2.5243. Min Act: -0.1700

Data Index: 3191756 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 2.7268. Min Range: -2.7268

Max Act: 2.5221. Min Act: -0.1700

Data Index: 6320426 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 2.7268. Min Range: -2.7268

Max Act: 2.5429. Min Act: -0.1700

Data Index: 5520717 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 2.7268. Min Range: -2.7268

Max Act: 2.5355. Min Act: -0.1700

Data Index: 5090582 (Open Web Text)

Max Activating Token Index: 1023