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

Dataset: Open Web Text

Neuron 2522 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: 3.7999. Min Range: -3.7999

Max Act: 3.7999. Min Act: -0.1700

Data Index: 1993090 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.7414. Min Act: -0.1700

Data Index: 8680314 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.7613. Min Act: -0.1700

Data Index: 3082477 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.7012. Min Act: -0.1700

Data Index: 6873839 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.6973. Min Act: -0.1700

Data Index: 3868180 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.7108. Min Act: -0.1700

Data Index: 5862635 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.6779. Min Act: -0.1700

Data Index: 6370092 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.6619. Min Act: -0.1700

Data Index: 895511 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.6748. Min Act: -0.1700

Data Index: 3718363 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.6748. Min Act: -0.1700

Data Index: 6885274 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.6706. Min Act: -0.1700

Data Index: 7679640 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.6735. Min Act: -0.1700

Data Index: 4647718 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.6839. Min Act: -0.1700

Data Index: 4317724 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.6444. Min Act: -0.1700

Data Index: 3635301 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.6503. Min Act: -0.1700

Data Index: 6700430 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.6406. Min Act: -0.1700

Data Index: 362365 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.6330. Min Act: -0.1700

Data Index: 6347162 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.6293. Min Act: -0.1700

Data Index: 2329371 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.6065. Min Act: -0.1700

Data Index: 4295747 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.6254. Min Act: -0.1700

Data Index: 1909883 (Open Web Text)

Max Activating Token Index: 6