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

Dataset: Open Web Text

Neuron 341 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: 4.1816. Min Range: -4.1816

Max Act: 4.1816. Min Act: -0.1700

Data Index: 607913 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.1816. Min Range: -4.1816

Max Act: 4.1517. Min Act: -0.1700

Data Index: 6177503 (Open Web Text)

Max Activating Token Index: 23

Text #2

Max Range: 4.1816. Min Range: -4.1816

Max Act: 4.1316. Min Act: -0.1700

Data Index: 8025934 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 4.1816. Min Range: -4.1816

Max Act: 4.1172. Min Act: -0.1700

Data Index: 950588 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 4.1816. Min Range: -4.1816

Max Act: 4.1172. Min Act: -0.1700

Data Index: 898432 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 4.1816. Min Range: -4.1816

Max Act: 4.0978. Min Act: -0.1700

Data Index: 8616930 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.1816. Min Range: -4.1816

Max Act: 4.0933. Min Act: -0.1700

Data Index: 5842955 (Open Web Text)

Max Activating Token Index: 976

Text #7

Max Range: 4.1816. Min Range: -4.1816

Max Act: 4.1172. Min Act: -0.1700

Data Index: 4038758 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 4.1816. Min Range: -4.1816

Max Act: 4.1172. Min Act: -0.1700

Data Index: 8515667 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 4.1816. Min Range: -4.1816

Max Act: 4.1172. Min Act: -0.1700

Data Index: 6931417 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 4.1816. Min Range: -4.1816

Max Act: 4.0936. Min Act: -0.1700

Data Index: 2103174 (Open Web Text)

Max Activating Token Index: 732

Text #11

Max Range: 4.1816. Min Range: -4.1816

Max Act: 4.0967. Min Act: -0.1700

Data Index: 3209708 (Open Web Text)

Max Activating Token Index: 580

Text #12

Max Range: 4.1816. Min Range: -4.1816

Max Act: 4.0752. Min Act: -0.1700

Data Index: 6511140 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.1816. Min Range: -4.1816

Max Act: 4.0483. Min Act: -0.1700

Data Index: 3492072 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.1816. Min Range: -4.1816

Max Act: 4.0446. Min Act: -0.1700

Data Index: 2446564 (Open Web Text)

Max Activating Token Index: 420

Text #15

Max Range: 4.1816. Min Range: -4.1816

Max Act: 4.0458. Min Act: -0.1700

Data Index: 3855241 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.1816. Min Range: -4.1816

Max Act: 4.0305. Min Act: -0.1700

Data Index: 8103684 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.1816. Min Range: -4.1816

Max Act: 4.0361. Min Act: -0.1700

Data Index: 6824057 (Open Web Text)

Max Activating Token Index: 569

Text #18

Max Range: 4.1816. Min Range: -4.1816

Max Act: 4.0262. Min Act: -0.1700

Data Index: 4354735 (Open Web Text)

Max Activating Token Index: 16

Text #19

Max Range: 4.1816. Min Range: -4.1816

Max Act: 4.0446. Min Act: -0.1700

Data Index: 643815 (Open Web Text)

Max Activating Token Index: 3