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

Dataset: Open Web Text

Neuron 73 in Layer 6

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: 4.4724. Min Range: -4.4724

Max Act: 4.4724. Min Act: -0.1700

Data Index: 4895475 (Open Web Text)

Max Activating Token Index: 718

Text #1

Max Range: 4.4724. Min Range: -4.4724

Max Act: 4.4688. Min Act: -0.1700

Data Index: 7074193 (Open Web Text)

Max Activating Token Index: 454

Text #2

Max Range: 4.4724. Min Range: -4.4724

Max Act: 4.4044. Min Act: -0.1700

Data Index: 6303562 (Open Web Text)

Max Activating Token Index: 1019

Text #3

Max Range: 4.4724. Min Range: -4.4724

Max Act: 4.3673. Min Act: -0.1700

Data Index: 5203778 (Open Web Text)

Max Activating Token Index: 148

Text #4

Max Range: 4.4724. Min Range: -4.4724

Max Act: 4.3355. Min Act: -0.1700

Data Index: 5650271 (Open Web Text)

Max Activating Token Index: 742

Text #5

Max Range: 4.4724. Min Range: -4.4724

Max Act: 4.3273. Min Act: -0.1700

Data Index: 8696403 (Open Web Text)

Max Activating Token Index: 947

Text #6

Max Range: 4.4724. Min Range: -4.4724

Max Act: 4.3152. Min Act: -0.1700

Data Index: 2534304 (Open Web Text)

Max Activating Token Index: 552

Text #7

Max Range: 4.4724. Min Range: -4.4724

Max Act: 4.3031. Min Act: -0.1700

Data Index: 2359653 (Open Web Text)

Max Activating Token Index: 835

Text #8

Max Range: 4.4724. Min Range: -4.4724

Max Act: 4.3071. Min Act: -0.1700

Data Index: 396211 (Open Web Text)

Max Activating Token Index: 934

Text #9

Max Range: 4.4724. Min Range: -4.4724

Max Act: 4.3117. Min Act: -0.1700

Data Index: 1439686 (Open Web Text)

Max Activating Token Index: 701

Text #10

Max Range: 4.4724. Min Range: -4.4724

Max Act: 4.2557. Min Act: -0.1700

Data Index: 5379140 (Open Web Text)

Max Activating Token Index: 623

Text #11

Max Range: 4.4724. Min Range: -4.4724

Max Act: 4.2508. Min Act: -0.1700

Data Index: 8830314 (Open Web Text)

Max Activating Token Index: 232

Text #12

Max Range: 4.4724. Min Range: -4.4724

Max Act: 4.2540. Min Act: -0.1700

Data Index: 6581653 (Open Web Text)

Max Activating Token Index: 558

Text #13

Max Range: 4.4724. Min Range: -4.4724

Max Act: 4.2651. Min Act: -0.1700

Data Index: 8787844 (Open Web Text)

Max Activating Token Index: 232

Text #14

Max Range: 4.4724. Min Range: -4.4724

Max Act: 4.2628. Min Act: -0.1700

Data Index: 3763737 (Open Web Text)

Max Activating Token Index: 972

Text #15

Max Range: 4.4724. Min Range: -4.4724

Max Act: 4.2498. Min Act: -0.1700

Data Index: 7275232 (Open Web Text)

Max Activating Token Index: 430

Text #16

Max Range: 4.4724. Min Range: -4.4724

Max Act: 4.2405. Min Act: -0.1700

Data Index: 2174107 (Open Web Text)

Max Activating Token Index: 998

Text #17

Max Range: 4.4724. Min Range: -4.4724

Max Act: 4.2243. Min Act: -0.1700

Data Index: 8006510 (Open Web Text)

Max Activating Token Index: 31

Text #18

Max Range: 4.4724. Min Range: -4.4724

Max Act: 4.2303. Min Act: -0.1700

Data Index: 2187837 (Open Web Text)

Max Activating Token Index: 487

Text #19

Max Range: 4.4724. Min Range: -4.4724

Max Act: 4.2236. Min Act: -0.1700

Data Index: 2278644 (Open Web Text)

Max Activating Token Index: 208