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

Dataset: Open Web Text

Neuron 710 in Layer 0

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: 0.8509. Min Range: -0.8509

Max Act: 0.8478. Min Act: -0.1700

Data Index: 7531311 (Open Web Text)

Max Activating Token Index: 48

Text #1

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8475. Min Act: -0.1700

Data Index: 544217 (Open Web Text)

Max Activating Token Index: 47

Text #2

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8509. Min Act: -0.1700

Data Index: 3286931 (Open Web Text)

Max Activating Token Index: 48

Text #3

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8370. Min Act: -0.1700

Data Index: 8209324 (Open Web Text)

Max Activating Token Index: 47

Text #4

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8329. Min Act: -0.1700

Data Index: 6771286 (Open Web Text)

Max Activating Token Index: 50

Text #5

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8415. Min Act: -0.1700

Data Index: 5536859 (Open Web Text)

Max Activating Token Index: 49

Text #6

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8211. Min Act: -0.1700

Data Index: 3721148 (Open Web Text)

Max Activating Token Index: 44

Text #7

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8183. Min Act: -0.1700

Data Index: 1516490 (Open Web Text)

Max Activating Token Index: 49

Text #8

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8278. Min Act: -0.1700

Data Index: 628357 (Open Web Text)

Max Activating Token Index: 50

Text #9

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8144. Min Act: -0.1700

Data Index: 4532570 (Open Web Text)

Max Activating Token Index: 47

Text #10

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8175. Min Act: -0.1700

Data Index: 4547282 (Open Web Text)

Max Activating Token Index: 50

Text #11

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8250. Min Act: -0.1700

Data Index: 206072 (Open Web Text)

Max Activating Token Index: 46

Text #12

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8192. Min Act: -0.1700

Data Index: 4554553 (Open Web Text)

Max Activating Token Index: 50

Text #13

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8197. Min Act: -0.1700

Data Index: 668236 (Open Web Text)

Max Activating Token Index: 52

Text #14

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8251. Min Act: -0.1700

Data Index: 5242081 (Open Web Text)

Max Activating Token Index: 51

Text #15

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8148. Min Act: -0.1700

Data Index: 5245492 (Open Web Text)

Max Activating Token Index: 52

Text #16

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8139. Min Act: -0.1700

Data Index: 2139050 (Open Web Text)

Max Activating Token Index: 52

Text #17

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8208. Min Act: -0.1700

Data Index: 5487337 (Open Web Text)

Max Activating Token Index: 50

Text #18

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8169. Min Act: -0.1700

Data Index: 3543472 (Open Web Text)

Max Activating Token Index: 48

Text #19

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8167. Min Act: -0.1700

Data Index: 1170029 (Open Web Text)

Max Activating Token Index: 47