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

Dataset: Open Web Text

Neuron 1638 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: 3.2537. Min Range: -3.2537

Max Act: 3.2537. Min Act: -0.1700

Data Index: 8043441 (Open Web Text)

Max Activating Token Index: 67

Text #1

Max Range: 3.2537. Min Range: -3.2537

Max Act: 3.2147. Min Act: -0.1700

Data Index: 8764511 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.2537. Min Range: -3.2537

Max Act: 3.2276. Min Act: -0.1700

Data Index: 4739179 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.2537. Min Range: -3.2537

Max Act: 3.2038. Min Act: -0.1700

Data Index: 3356619 (Open Web Text)

Max Activating Token Index: 17

Text #4

Max Range: 3.2537. Min Range: -3.2537

Max Act: 3.2118. Min Act: -0.1700

Data Index: 4954021 (Open Web Text)

Max Activating Token Index: 40

Text #5

Max Range: 3.2537. Min Range: -3.2537

Max Act: 3.2098. Min Act: -0.1700

Data Index: 2723744 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.2537. Min Range: -3.2537

Max Act: 3.2084. Min Act: -0.1700

Data Index: 6552852 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 3.2537. Min Range: -3.2537

Max Act: 3.2100. Min Act: -0.1700

Data Index: 1078715 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.2537. Min Range: -3.2537

Max Act: 3.2118. Min Act: -0.1700

Data Index: 1783359 (Open Web Text)

Max Activating Token Index: 23

Text #9

Max Range: 3.2537. Min Range: -3.2537

Max Act: 3.1950. Min Act: -0.1700

Data Index: 4347605 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 3.2537. Min Range: -3.2537

Max Act: 3.1891. Min Act: -0.1700

Data Index: 6512291 (Open Web Text)

Max Activating Token Index: 874

Text #11

Max Range: 3.2537. Min Range: -3.2537

Max Act: 3.1890. Min Act: -0.1700

Data Index: 4097653 (Open Web Text)

Max Activating Token Index: 23

Text #12

Max Range: 3.2537. Min Range: -3.2537

Max Act: 3.1860. Min Act: -0.1700

Data Index: 3612850 (Open Web Text)

Max Activating Token Index: 135

Text #13

Max Range: 3.2537. Min Range: -3.2537

Max Act: 3.1855. Min Act: -0.1700

Data Index: 5099033 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.2537. Min Range: -3.2537

Max Act: 3.1696. Min Act: -0.1700

Data Index: 1007082 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 3.2537. Min Range: -3.2537

Max Act: 3.1705. Min Act: -0.1700

Data Index: 1323540 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.2537. Min Range: -3.2537

Max Act: 3.1740. Min Act: -0.1700

Data Index: 5225305 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.2537. Min Range: -3.2537

Max Act: 3.1654. Min Act: -0.1700

Data Index: 3787482 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.2537. Min Range: -3.2537

Max Act: 3.1550. Min Act: -0.1700

Data Index: 5309522 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.2537. Min Range: -3.2537

Max Act: 3.1519. Min Act: -0.1700

Data Index: 5756226 (Open Web Text)

Max Activating Token Index: 19