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

Dataset: Open Web Text

Neuron 353 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: 4.1201. Min Range: -4.1201

Max Act: 4.1201. Min Act: -0.1700

Data Index: 4504979 (Open Web Text)

Max Activating Token Index: 847

Text #1

Max Range: 4.1201. Min Range: -4.1201

Max Act: 4.1178. Min Act: -0.1700

Data Index: 7985407 (Open Web Text)

Max Activating Token Index: 220

Text #2

Max Range: 4.1201. Min Range: -4.1201

Max Act: 4.1150. Min Act: -0.1700

Data Index: 5064810 (Open Web Text)

Max Activating Token Index: 30

Text #3

Max Range: 4.1201. Min Range: -4.1201

Max Act: 4.1002. Min Act: -0.1700

Data Index: 2668015 (Open Web Text)

Max Activating Token Index: 369

Text #4

Max Range: 4.1201. Min Range: -4.1201

Max Act: 4.0435. Min Act: -0.1700

Data Index: 334877 (Open Web Text)

Max Activating Token Index: 572

Text #5

Max Range: 4.1201. Min Range: -4.1201

Max Act: 3.9764. Min Act: -0.1700

Data Index: 6763241 (Open Web Text)

Max Activating Token Index: 82

Text #6

Max Range: 4.1201. Min Range: -4.1201

Max Act: 4.0022. Min Act: -0.1700

Data Index: 3118703 (Open Web Text)

Max Activating Token Index: 981

Text #7

Max Range: 4.1201. Min Range: -4.1201

Max Act: 3.9956. Min Act: -0.1700

Data Index: 1640433 (Open Web Text)

Max Activating Token Index: 271

Text #8

Max Range: 4.1201. Min Range: -4.1201

Max Act: 3.9761. Min Act: -0.1700

Data Index: 6598981 (Open Web Text)

Max Activating Token Index: 859

Text #9

Max Range: 4.1201. Min Range: -4.1201

Max Act: 3.9503. Min Act: -0.1700

Data Index: 8201146 (Open Web Text)

Max Activating Token Index: 510

Text #10

Max Range: 4.1201. Min Range: -4.1201

Max Act: 3.9703. Min Act: -0.1700

Data Index: 1392919 (Open Web Text)

Max Activating Token Index: 622

Text #11

Max Range: 4.1201. Min Range: -4.1201

Max Act: 3.9831. Min Act: -0.1700

Data Index: 4849597 (Open Web Text)

Max Activating Token Index: 952

Text #12

Max Range: 4.1201. Min Range: -4.1201

Max Act: 3.9423. Min Act: -0.1700

Data Index: 8767578 (Open Web Text)

Max Activating Token Index: 576

Text #13

Max Range: 4.1201. Min Range: -4.1201

Max Act: 3.9231. Min Act: -0.1700

Data Index: 4709753 (Open Web Text)

Max Activating Token Index: 850

Text #14

Max Range: 4.1201. Min Range: -4.1201

Max Act: 3.8963. Min Act: -0.1700

Data Index: 8515225 (Open Web Text)

Max Activating Token Index: 256

Text #15

Max Range: 4.1201. Min Range: -4.1201

Max Act: 3.8816. Min Act: -0.1700

Data Index: 2782753 (Open Web Text)

Max Activating Token Index: 488

Text #16

Max Range: 4.1201. Min Range: -4.1201

Max Act: 3.8948. Min Act: -0.1700

Data Index: 7039082 (Open Web Text)

Max Activating Token Index: 168

Text #17

Max Range: 4.1201. Min Range: -4.1201

Max Act: 3.9076. Min Act: -0.1700

Data Index: 4289324 (Open Web Text)

Max Activating Token Index: 787

Text #18

Max Range: 4.1201. Min Range: -4.1201

Max Act: 3.8446. Min Act: -0.1700

Data Index: 6304002 (Open Web Text)

Max Activating Token Index: 525

Text #19

Max Range: 4.1201. Min Range: -4.1201

Max Act: 3.8820. Min Act: -0.1700

Data Index: 6457387 (Open Web Text)

Max Activating Token Index: 438