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

Dataset: Open Web Text

Neuron 2444 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: 3.8052. Min Range: -3.8052

Max Act: 3.8052. Min Act: -0.1700

Data Index: 5550136 (Open Web Text)

Max Activating Token Index: 709

Text #1

Max Range: 3.8052. Min Range: -3.8052

Max Act: 3.7405. Min Act: -0.1700

Data Index: 7590492 (Open Web Text)

Max Activating Token Index: 231

Text #2

Max Range: 3.8052. Min Range: -3.8052

Max Act: 3.6987. Min Act: -0.1700

Data Index: 7773788 (Open Web Text)

Max Activating Token Index: 520

Text #3

Max Range: 3.8052. Min Range: -3.8052

Max Act: 3.6229. Min Act: -0.1700

Data Index: 7135585 (Open Web Text)

Max Activating Token Index: 140

Text #4

Max Range: 3.8052. Min Range: -3.8052

Max Act: 3.6159. Min Act: -0.1700

Data Index: 3260718 (Open Web Text)

Max Activating Token Index: 914

Text #5

Max Range: 3.8052. Min Range: -3.8052

Max Act: 3.6177. Min Act: -0.1700

Data Index: 3050690 (Open Web Text)

Max Activating Token Index: 952

Text #6

Max Range: 3.8052. Min Range: -3.8052

Max Act: 3.6332. Min Act: -0.1700

Data Index: 8174392 (Open Web Text)

Max Activating Token Index: 205

Text #7

Max Range: 3.8052. Min Range: -3.8052

Max Act: 3.5761. Min Act: -0.1700

Data Index: 6811411 (Open Web Text)

Max Activating Token Index: 208

Text #8

Max Range: 3.8052. Min Range: -3.8052

Max Act: 3.5720. Min Act: -0.1700

Data Index: 7058602 (Open Web Text)

Max Activating Token Index: 399

Text #9

Max Range: 3.8052. Min Range: -3.8052

Max Act: 3.5594. Min Act: -0.1700

Data Index: 7866688 (Open Web Text)

Max Activating Token Index: 1004

Text #10

Max Range: 3.8052. Min Range: -3.8052

Max Act: 3.5314. Min Act: -0.1700

Data Index: 5300750 (Open Web Text)

Max Activating Token Index: 195

Text #11

Max Range: 3.8052. Min Range: -3.8052

Max Act: 3.5359. Min Act: -0.1700

Data Index: 8231705 (Open Web Text)

Max Activating Token Index: 19

Text #12

Max Range: 3.8052. Min Range: -3.8052

Max Act: 3.5109. Min Act: -0.1700

Data Index: 4694408 (Open Web Text)

Max Activating Token Index: 885

Text #13

Max Range: 3.8052. Min Range: -3.8052

Max Act: 3.5377. Min Act: -0.1700

Data Index: 8429157 (Open Web Text)

Max Activating Token Index: 818

Text #14

Max Range: 3.8052. Min Range: -3.8052

Max Act: 3.5502. Min Act: -0.1700

Data Index: 4792176 (Open Web Text)

Max Activating Token Index: 932

Text #15

Max Range: 3.8052. Min Range: -3.8052

Max Act: 3.5356. Min Act: -0.1700

Data Index: 7403304 (Open Web Text)

Max Activating Token Index: 79

Text #16

Max Range: 3.8052. Min Range: -3.8052

Max Act: 3.5185. Min Act: -0.1700

Data Index: 3661736 (Open Web Text)

Max Activating Token Index: 479

Text #17

Max Range: 3.8052. Min Range: -3.8052

Max Act: 3.5111. Min Act: -0.1700

Data Index: 7175540 (Open Web Text)

Max Activating Token Index: 544

Text #18

Max Range: 3.8052. Min Range: -3.8052

Max Act: 3.4951. Min Act: -0.1700

Data Index: 4585273 (Open Web Text)

Max Activating Token Index: 331

Text #19

Max Range: 3.8052. Min Range: -3.8052

Max Act: 3.4960. Min Act: -0.1700

Data Index: 2924731 (Open Web Text)

Max Activating Token Index: 175