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

Dataset: Open Web Text

Neuron 1860 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: 4.6163. Min Range: -4.6163

Max Act: 4.6163. Min Act: -0.1700

Data Index: 671675 (Open Web Text)

Max Activating Token Index: 42

Text #1

Max Range: 4.6163. Min Range: -4.6163

Max Act: 4.5732. Min Act: -0.1700

Data Index: 6507879 (Open Web Text)

Max Activating Token Index: 832

Text #2

Max Range: 4.6163. Min Range: -4.6163

Max Act: 4.5491. Min Act: -0.1700

Data Index: 2992184 (Open Web Text)

Max Activating Token Index: 974

Text #3

Max Range: 4.6163. Min Range: -4.6163

Max Act: 4.5098. Min Act: -0.1700

Data Index: 3707591 (Open Web Text)

Max Activating Token Index: 985

Text #4

Max Range: 4.6163. Min Range: -4.6163

Max Act: 4.5171. Min Act: -0.1700

Data Index: 4233696 (Open Web Text)

Max Activating Token Index: 482

Text #5

Max Range: 4.6163. Min Range: -4.6163

Max Act: 4.5188. Min Act: -0.1700

Data Index: 1963500 (Open Web Text)

Max Activating Token Index: 126

Text #6

Max Range: 4.6163. Min Range: -4.6163

Max Act: 4.5444. Min Act: -0.1700

Data Index: 2104304 (Open Web Text)

Max Activating Token Index: 989

Text #7

Max Range: 4.6163. Min Range: -4.6163

Max Act: 4.5239. Min Act: -0.1700

Data Index: 8315260 (Open Web Text)

Max Activating Token Index: 18

Text #8

Max Range: 4.6163. Min Range: -4.6163

Max Act: 4.4912. Min Act: -0.1700

Data Index: 946831 (Open Web Text)

Max Activating Token Index: 457

Text #9

Max Range: 4.6163. Min Range: -4.6163

Max Act: 4.5288. Min Act: -0.1700

Data Index: 6707322 (Open Web Text)

Max Activating Token Index: 206

Text #10

Max Range: 4.6163. Min Range: -4.6163

Max Act: 4.4946. Min Act: -0.1700

Data Index: 6538757 (Open Web Text)

Max Activating Token Index: 528

Text #11

Max Range: 4.6163. Min Range: -4.6163

Max Act: 4.4535. Min Act: -0.1700

Data Index: 382605 (Open Web Text)

Max Activating Token Index: 529

Text #12

Max Range: 4.6163. Min Range: -4.6163

Max Act: 4.5125. Min Act: -0.1700

Data Index: 342347 (Open Web Text)

Max Activating Token Index: 18

Text #13

Max Range: 4.6163. Min Range: -4.6163

Max Act: 4.4844. Min Act: -0.1700

Data Index: 2504955 (Open Web Text)

Max Activating Token Index: 419

Text #14

Max Range: 4.6163. Min Range: -4.6163

Max Act: 4.4861. Min Act: -0.1700

Data Index: 6888288 (Open Web Text)

Max Activating Token Index: 201

Text #15

Max Range: 4.6163. Min Range: -4.6163

Max Act: 4.4827. Min Act: -0.1700

Data Index: 1631654 (Open Web Text)

Max Activating Token Index: 910

Text #16

Max Range: 4.6163. Min Range: -4.6163

Max Act: 4.4820. Min Act: -0.1700

Data Index: 2464047 (Open Web Text)

Max Activating Token Index: 535

Text #17

Max Range: 4.6163. Min Range: -4.6163

Max Act: 4.4810. Min Act: -0.1700

Data Index: 2301449 (Open Web Text)

Max Activating Token Index: 143

Text #18

Max Range: 4.6163. Min Range: -4.6163

Max Act: 4.4601. Min Act: -0.1700

Data Index: 2957017 (Open Web Text)

Max Activating Token Index: 807

Text #19

Max Range: 4.6163. Min Range: -4.6163

Max Act: 4.4647. Min Act: -0.1700

Data Index: 424908 (Open Web Text)

Max Activating Token Index: 130