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

Dataset: Open Web Text

Neuron 231 in Layer 0

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: 4.9450. Min Range: -4.9450

Max Act: 4.9450. Min Act: -0.1700

Data Index: 6487897 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.9450. Min Range: -4.9450

Max Act: 4.9170. Min Act: -0.1700

Data Index: 5305891 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.9450. Min Range: -4.9450

Max Act: 4.8854. Min Act: -0.1700

Data Index: 8390112 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 4.9450. Min Range: -4.9450

Max Act: 4.8762. Min Act: -0.1700

Data Index: 6507573 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.9450. Min Range: -4.9450

Max Act: 4.8888. Min Act: -0.1700

Data Index: 6502335 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 4.9450. Min Range: -4.9450

Max Act: 4.8869. Min Act: -0.1700

Data Index: 1370880 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.9450. Min Range: -4.9450

Max Act: 4.8830. Min Act: -0.1700

Data Index: 1731676 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.9450. Min Range: -4.9450

Max Act: 4.8791. Min Act: -0.1700

Data Index: 8746219 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.9450. Min Range: -4.9450

Max Act: 4.8734. Min Act: -0.1700

Data Index: 8725047 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 4.9450. Min Range: -4.9450

Max Act: 4.8371. Min Act: -0.1700

Data Index: 3633899 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.9450. Min Range: -4.9450

Max Act: 4.8638. Min Act: -0.1700

Data Index: 1852260 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.9450. Min Range: -4.9450

Max Act: 4.8569. Min Act: -0.1700

Data Index: 461629 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 4.9450. Min Range: -4.9450

Max Act: 4.8332. Min Act: -0.1700

Data Index: 2341892 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.9450. Min Range: -4.9450

Max Act: 4.8015. Min Act: -0.1700

Data Index: 1339082 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.9450. Min Range: -4.9450

Max Act: 4.8336. Min Act: -0.1700

Data Index: 1067971 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.9450. Min Range: -4.9450

Max Act: 4.8170. Min Act: -0.1700

Data Index: 30048 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.9450. Min Range: -4.9450

Max Act: 4.8071. Min Act: -0.1700

Data Index: 367820 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.9450. Min Range: -4.9450

Max Act: 4.8372. Min Act: -0.1700

Data Index: 3542183 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.9450. Min Range: -4.9450

Max Act: 4.8321. Min Act: -0.1700

Data Index: 1546264 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.9450. Min Range: -4.9450

Max Act: 4.8002. Min Act: -0.1700

Data Index: 4239523 (Open Web Text)

Max Activating Token Index: 6