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

Dataset: Open Web Text

Neuron 357 in Layer 5

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: 4.0045. Min Range: -4.0045

Max Act: 4.0045. Min Act: -0.1700

Data Index: 3808202 (Open Web Text)

Max Activating Token Index: 318

Text #1

Max Range: 4.0045. Min Range: -4.0045

Max Act: 3.7956. Min Act: -0.1700

Data Index: 4488964 (Open Web Text)

Max Activating Token Index: 701

Text #2

Max Range: 4.0045. Min Range: -4.0045

Max Act: 3.7439. Min Act: -0.1700

Data Index: 1710413 (Open Web Text)

Max Activating Token Index: 895

Text #3

Max Range: 4.0045. Min Range: -4.0045

Max Act: 3.7163. Min Act: -0.1700

Data Index: 8366325 (Open Web Text)

Max Activating Token Index: 232

Text #4

Max Range: 4.0045. Min Range: -4.0045

Max Act: 3.7025. Min Act: -0.1700

Data Index: 4102324 (Open Web Text)

Max Activating Token Index: 889

Text #5

Max Range: 4.0045. Min Range: -4.0045

Max Act: 3.6789. Min Act: -0.1700

Data Index: 2466588 (Open Web Text)

Max Activating Token Index: 206

Text #6

Max Range: 4.0045. Min Range: -4.0045

Max Act: 3.6983. Min Act: -0.1700

Data Index: 1004642 (Open Web Text)

Max Activating Token Index: 554

Text #7

Max Range: 4.0045. Min Range: -4.0045

Max Act: 3.6368. Min Act: -0.1700

Data Index: 6030251 (Open Web Text)

Max Activating Token Index: 287

Text #8

Max Range: 4.0045. Min Range: -4.0045

Max Act: 3.6473. Min Act: -0.1700

Data Index: 5567961 (Open Web Text)

Max Activating Token Index: 257

Text #9

Max Range: 4.0045. Min Range: -4.0045

Max Act: 3.6533. Min Act: -0.1700

Data Index: 7822292 (Open Web Text)

Max Activating Token Index: 1017

Text #10

Max Range: 4.0045. Min Range: -4.0045

Max Act: 3.6295. Min Act: -0.1700

Data Index: 8420566 (Open Web Text)

Max Activating Token Index: 87

Text #11

Max Range: 4.0045. Min Range: -4.0045

Max Act: 3.6386. Min Act: -0.1700

Data Index: 908512 (Open Web Text)

Max Activating Token Index: 429

Text #12

Max Range: 4.0045. Min Range: -4.0045

Max Act: 3.5980. Min Act: -0.1700

Data Index: 4355799 (Open Web Text)

Max Activating Token Index: 245

Text #13

Max Range: 4.0045. Min Range: -4.0045

Max Act: 3.6139. Min Act: -0.1700

Data Index: 5345857 (Open Web Text)

Max Activating Token Index: 763

Text #14

Max Range: 4.0045. Min Range: -4.0045

Max Act: 3.5771. Min Act: -0.1700

Data Index: 6295691 (Open Web Text)

Max Activating Token Index: 983

Text #15

Max Range: 4.0045. Min Range: -4.0045

Max Act: 3.5758. Min Act: -0.1700

Data Index: 2124938 (Open Web Text)

Max Activating Token Index: 302

Text #16

Max Range: 4.0045. Min Range: -4.0045

Max Act: 3.6149. Min Act: -0.1700

Data Index: 1274672 (Open Web Text)

Max Activating Token Index: 483

Text #17

Max Range: 4.0045. Min Range: -4.0045

Max Act: 3.5733. Min Act: -0.1700

Data Index: 5286616 (Open Web Text)

Max Activating Token Index: 481

Text #18

Max Range: 4.0045. Min Range: -4.0045

Max Act: 3.5531. Min Act: -0.1700

Data Index: 6850282 (Open Web Text)

Max Activating Token Index: 247

Text #19

Max Range: 4.0045. Min Range: -4.0045

Max Act: 3.5749. Min Act: -0.1700

Data Index: 2045819 (Open Web Text)

Max Activating Token Index: 786