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

Dataset: Open Web Text

Neuron 1158 in Layer 3

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: 3.6132. Min Range: -3.6132

Max Act: 3.6132. Min Act: -0.1700

Data Index: 6417407 (Open Web Text)

Max Activating Token Index: 552

Text #1

Max Range: 3.6132. Min Range: -3.6132

Max Act: 3.5568. Min Act: -0.1700

Data Index: 3052859 (Open Web Text)

Max Activating Token Index: 176

Text #2

Max Range: 3.6132. Min Range: -3.6132

Max Act: 3.5801. Min Act: -0.1700

Data Index: 6238551 (Open Web Text)

Max Activating Token Index: 332

Text #3

Max Range: 3.6132. Min Range: -3.6132

Max Act: 3.6038. Min Act: -0.1700

Data Index: 8688120 (Open Web Text)

Max Activating Token Index: 291

Text #4

Max Range: 3.6132. Min Range: -3.6132

Max Act: 3.5378. Min Act: -0.1700

Data Index: 5493723 (Open Web Text)

Max Activating Token Index: 1009

Text #5

Max Range: 3.6132. Min Range: -3.6132

Max Act: 3.5625. Min Act: -0.1700

Data Index: 6649679 (Open Web Text)

Max Activating Token Index: 1001

Text #6

Max Range: 3.6132. Min Range: -3.6132

Max Act: 3.4989. Min Act: -0.1700

Data Index: 2343419 (Open Web Text)

Max Activating Token Index: 429

Text #7

Max Range: 3.6132. Min Range: -3.6132

Max Act: 3.5252. Min Act: -0.1700

Data Index: 4344033 (Open Web Text)

Max Activating Token Index: 784

Text #8

Max Range: 3.6132. Min Range: -3.6132

Max Act: 3.4580. Min Act: -0.1700

Data Index: 5211234 (Open Web Text)

Max Activating Token Index: 190

Text #9

Max Range: 3.6132. Min Range: -3.6132

Max Act: 3.4946. Min Act: -0.1700

Data Index: 5999646 (Open Web Text)

Max Activating Token Index: 837

Text #10

Max Range: 3.6132. Min Range: -3.6132

Max Act: 3.4894. Min Act: -0.1700

Data Index: 1389630 (Open Web Text)

Max Activating Token Index: 26

Text #11

Max Range: 3.6132. Min Range: -3.6132

Max Act: 3.4373. Min Act: -0.1700

Data Index: 4569497 (Open Web Text)

Max Activating Token Index: 439

Text #12

Max Range: 3.6132. Min Range: -3.6132

Max Act: 3.4190. Min Act: -0.1700

Data Index: 3917886 (Open Web Text)

Max Activating Token Index: 388

Text #13

Max Range: 3.6132. Min Range: -3.6132

Max Act: 3.4545. Min Act: -0.1700

Data Index: 1221822 (Open Web Text)

Max Activating Token Index: 347

Text #14

Max Range: 3.6132. Min Range: -3.6132

Max Act: 3.4524. Min Act: -0.1700

Data Index: 3007692 (Open Web Text)

Max Activating Token Index: 61

Text #15

Max Range: 3.6132. Min Range: -3.6132

Max Act: 3.4192. Min Act: -0.1700

Data Index: 3365625 (Open Web Text)

Max Activating Token Index: 751

Text #16

Max Range: 3.6132. Min Range: -3.6132

Max Act: 3.4467. Min Act: -0.1700

Data Index: 5536873 (Open Web Text)

Max Activating Token Index: 389

Text #17

Max Range: 3.6132. Min Range: -3.6132

Max Act: 3.4141. Min Act: -0.1700

Data Index: 7694664 (Open Web Text)

Max Activating Token Index: 945

Text #18

Max Range: 3.6132. Min Range: -3.6132

Max Act: 3.4137. Min Act: -0.1700

Data Index: 426257 (Open Web Text)

Max Activating Token Index: 142

Text #19

Max Range: 3.6132. Min Range: -3.6132

Max Act: 3.4240. Min Act: -0.1700

Data Index: 3204049 (Open Web Text)

Max Activating Token Index: 224