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

Dataset: Open Web Text

Neuron 957 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: 2.7526. Min Range: -2.7526

Max Act: 2.7526. Min Act: -0.1700

Data Index: 7296209 (Open Web Text)

Max Activating Token Index: 391

Text #1

Max Range: 2.7526. Min Range: -2.7526

Max Act: 2.7356. Min Act: -0.1700

Data Index: 3033597 (Open Web Text)

Max Activating Token Index: 407

Text #2

Max Range: 2.7526. Min Range: -2.7526

Max Act: 2.6956. Min Act: -0.1700

Data Index: 1274235 (Open Web Text)

Max Activating Token Index: 1009

Text #3

Max Range: 2.7526. Min Range: -2.7526

Max Act: 2.5802. Min Act: -0.1700

Data Index: 1840704 (Open Web Text)

Max Activating Token Index: 757

Text #4

Max Range: 2.7526. Min Range: -2.7526

Max Act: 2.5996. Min Act: -0.1700

Data Index: 1351690 (Open Web Text)

Max Activating Token Index: 980

Text #5

Max Range: 2.7526. Min Range: -2.7526

Max Act: 2.5928. Min Act: -0.1700

Data Index: 6176336 (Open Web Text)

Max Activating Token Index: 949

Text #6

Max Range: 2.7526. Min Range: -2.7526

Max Act: 2.6024. Min Act: -0.1700

Data Index: 7398179 (Open Web Text)

Max Activating Token Index: 69

Text #7

Max Range: 2.7526. Min Range: -2.7526

Max Act: 2.5732. Min Act: -0.1700

Data Index: 1124118 (Open Web Text)

Max Activating Token Index: 320

Text #8

Max Range: 2.7526. Min Range: -2.7526

Max Act: 2.6152. Min Act: -0.1700

Data Index: 2248053 (Open Web Text)

Max Activating Token Index: 438

Text #9

Max Range: 2.7526. Min Range: -2.7526

Max Act: 2.5720. Min Act: -0.1700

Data Index: 5824428 (Open Web Text)

Max Activating Token Index: 139

Text #10

Max Range: 2.7526. Min Range: -2.7526

Max Act: 2.5180. Min Act: -0.1700

Data Index: 1538108 (Open Web Text)

Max Activating Token Index: 391

Text #11

Max Range: 2.7526. Min Range: -2.7526

Max Act: 2.5237. Min Act: -0.1700

Data Index: 5777825 (Open Web Text)

Max Activating Token Index: 318

Text #12

Max Range: 2.7526. Min Range: -2.7526

Max Act: 2.5113. Min Act: -0.1700

Data Index: 8407311 (Open Web Text)

Max Activating Token Index: 553

Text #13

Max Range: 2.7526. Min Range: -2.7526

Max Act: 2.5295. Min Act: -0.1700

Data Index: 3023004 (Open Web Text)

Max Activating Token Index: 823

Text #14

Max Range: 2.7526. Min Range: -2.7526

Max Act: 2.4871. Min Act: -0.1700

Data Index: 3239528 (Open Web Text)

Max Activating Token Index: 34

Text #15

Max Range: 2.7526. Min Range: -2.7526

Max Act: 2.4935. Min Act: -0.1700

Data Index: 7004086 (Open Web Text)

Max Activating Token Index: 382

Text #16

Max Range: 2.7526. Min Range: -2.7526

Max Act: 2.5085. Min Act: -0.1700

Data Index: 7181706 (Open Web Text)

Max Activating Token Index: 69

Text #17

Max Range: 2.7526. Min Range: -2.7526

Max Act: 2.5305. Min Act: -0.1700

Data Index: 7307950 (Open Web Text)

Max Activating Token Index: 939

Text #18

Max Range: 2.7526. Min Range: -2.7526

Max Act: 2.4904. Min Act: -0.1700

Data Index: 4237139 (Open Web Text)

Max Activating Token Index: 829

Text #19

Max Range: 2.7526. Min Range: -2.7526

Max Act: 2.4836. Min Act: -0.1700

Data Index: 1904062 (Open Web Text)

Max Activating Token Index: 496