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

Dataset: Open Web Text

Neuron 2553 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: 3.0960. Min Range: -3.0960

Max Act: 3.0960. Min Act: -0.1700

Data Index: 8832619 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.0960. Min Range: -3.0960

Max Act: 3.0396. Min Act: -0.1700

Data Index: 7884937 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 3.0960. Min Range: -3.0960

Max Act: 3.0283. Min Act: -0.1700

Data Index: 8819035 (Open Web Text)

Max Activating Token Index: 93

Text #3

Max Range: 3.0960. Min Range: -3.0960

Max Act: 2.9613. Min Act: -0.1700

Data Index: 7526 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 3.0960. Min Range: -3.0960

Max Act: 2.9457. Min Act: -0.1700

Data Index: 7986313 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.0960. Min Range: -3.0960

Max Act: 2.9414. Min Act: -0.1700

Data Index: 8193479 (Open Web Text)

Max Activating Token Index: 704

Text #6

Max Range: 3.0960. Min Range: -3.0960

Max Act: 2.9268. Min Act: -0.1700

Data Index: 4178017 (Open Web Text)

Max Activating Token Index: 300

Text #7

Max Range: 3.0960. Min Range: -3.0960

Max Act: 2.9253. Min Act: -0.1700

Data Index: 2851573 (Open Web Text)

Max Activating Token Index: 370

Text #8

Max Range: 3.0960. Min Range: -3.0960

Max Act: 2.9342. Min Act: -0.1700

Data Index: 7940186 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 3.0960. Min Range: -3.0960

Max Act: 2.9381. Min Act: -0.1700

Data Index: 2552451 (Open Web Text)

Max Activating Token Index: 990

Text #10

Max Range: 3.0960. Min Range: -3.0960

Max Act: 2.9229. Min Act: -0.1700

Data Index: 2458368 (Open Web Text)

Max Activating Token Index: 332

Text #11

Max Range: 3.0960. Min Range: -3.0960

Max Act: 2.9370. Min Act: -0.1700

Data Index: 7902215 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 3.0960. Min Range: -3.0960

Max Act: 2.9320. Min Act: -0.1700

Data Index: 5982081 (Open Web Text)

Max Activating Token Index: 941

Text #13

Max Range: 3.0960. Min Range: -3.0960

Max Act: 2.9239. Min Act: -0.1700

Data Index: 7830177 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.0960. Min Range: -3.0960

Max Act: 2.9311. Min Act: -0.1700

Data Index: 6539744 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.0960. Min Range: -3.0960

Max Act: 2.9334. Min Act: -0.1700

Data Index: 1082576 (Open Web Text)

Max Activating Token Index: 652

Text #16

Max Range: 3.0960. Min Range: -3.0960

Max Act: 2.9276. Min Act: -0.1700

Data Index: 8237012 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 3.0960. Min Range: -3.0960

Max Act: 2.9332. Min Act: -0.1700

Data Index: 210784 (Open Web Text)

Max Activating Token Index: 41

Text #18

Max Range: 3.0960. Min Range: -3.0960

Max Act: 2.9383. Min Act: -0.1700

Data Index: 6016583 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 3.0960. Min Range: -3.0960

Max Act: 2.9126. Min Act: -0.1700

Data Index: 2777950 (Open Web Text)

Max Activating Token Index: 5