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

Dataset: Open Web Text

Neuron 2140 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: 5.8085. Min Range: -5.8085

Max Act: 5.8085. Min Act: -0.1700

Data Index: 6916470 (Open Web Text)

Max Activating Token Index: 554

Text #1

Max Range: 5.8085. Min Range: -5.8085

Max Act: 5.7886. Min Act: -0.1700

Data Index: 3703394 (Open Web Text)

Max Activating Token Index: 482

Text #2

Max Range: 5.8085. Min Range: -5.8085

Max Act: 5.5294. Min Act: -0.1700

Data Index: 6873850 (Open Web Text)

Max Activating Token Index: 254

Text #3

Max Range: 5.8085. Min Range: -5.8085

Max Act: 5.5338. Min Act: -0.1700

Data Index: 5583239 (Open Web Text)

Max Activating Token Index: 962

Text #4

Max Range: 5.8085. Min Range: -5.8085

Max Act: 5.4831. Min Act: -0.1700

Data Index: 8527730 (Open Web Text)

Max Activating Token Index: 418

Text #5

Max Range: 5.8085. Min Range: -5.8085

Max Act: 5.4059. Min Act: -0.1700

Data Index: 7361290 (Open Web Text)

Max Activating Token Index: 951

Text #6

Max Range: 5.8085. Min Range: -5.8085

Max Act: 5.3470. Min Act: -0.1700

Data Index: 871686 (Open Web Text)

Max Activating Token Index: 140

Text #7

Max Range: 5.8085. Min Range: -5.8085

Max Act: 5.4261. Min Act: -0.1700

Data Index: 4329711 (Open Web Text)

Max Activating Token Index: 599

Text #8

Max Range: 5.8085. Min Range: -5.8085

Max Act: 5.3774. Min Act: -0.1700

Data Index: 4636789 (Open Web Text)

Max Activating Token Index: 850

Text #9

Max Range: 5.8085. Min Range: -5.8085

Max Act: 5.3367. Min Act: -0.1700

Data Index: 5637869 (Open Web Text)

Max Activating Token Index: 850

Text #10

Max Range: 5.8085. Min Range: -5.8085

Max Act: 5.3402. Min Act: -0.1700

Data Index: 4798763 (Open Web Text)

Max Activating Token Index: 522

Text #11

Max Range: 5.8085. Min Range: -5.8085

Max Act: 5.2776. Min Act: -0.1700

Data Index: 2638101 (Open Web Text)

Max Activating Token Index: 375

Text #12

Max Range: 5.8085. Min Range: -5.8085

Max Act: 5.2816. Min Act: -0.1700

Data Index: 90975 (Open Web Text)

Max Activating Token Index: 1016

Text #13

Max Range: 5.8085. Min Range: -5.8085

Max Act: 5.3176. Min Act: -0.1700

Data Index: 2727411 (Open Web Text)

Max Activating Token Index: 348

Text #14

Max Range: 5.8085. Min Range: -5.8085

Max Act: 5.2328. Min Act: -0.1700

Data Index: 209851 (Open Web Text)

Max Activating Token Index: 584

Text #15

Max Range: 5.8085. Min Range: -5.8085

Max Act: 5.2789. Min Act: -0.1700

Data Index: 7796203 (Open Web Text)

Max Activating Token Index: 135

Text #16

Max Range: 5.8085. Min Range: -5.8085

Max Act: 5.2417. Min Act: -0.1700

Data Index: 3681082 (Open Web Text)

Max Activating Token Index: 146

Text #17

Max Range: 5.8085. Min Range: -5.8085

Max Act: 5.2342. Min Act: -0.1700

Data Index: 7497379 (Open Web Text)

Max Activating Token Index: 239

Text #18

Max Range: 5.8085. Min Range: -5.8085

Max Act: 5.2100. Min Act: -0.1700

Data Index: 2162268 (Open Web Text)

Max Activating Token Index: 522

Text #19

Max Range: 5.8085. Min Range: -5.8085

Max Act: 5.2337. Min Act: -0.1700

Data Index: 8111650 (Open Web Text)

Max Activating Token Index: 138