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

Dataset: Open Web Text

Neuron 1630 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: 3.4170. Min Range: -3.4170

Max Act: 3.4170. Min Act: -0.1700

Data Index: 581532 (Open Web Text)

Max Activating Token Index: 167

Text #1

Max Range: 3.4170. Min Range: -3.4170

Max Act: 3.3815. Min Act: -0.1700

Data Index: 6853093 (Open Web Text)

Max Activating Token Index: 246

Text #2

Max Range: 3.4170. Min Range: -3.4170

Max Act: 3.3753. Min Act: -0.1700

Data Index: 2189255 (Open Web Text)

Max Activating Token Index: 295

Text #3

Max Range: 3.4170. Min Range: -3.4170

Max Act: 3.3791. Min Act: -0.1700

Data Index: 4222484 (Open Web Text)

Max Activating Token Index: 419

Text #4

Max Range: 3.4170. Min Range: -3.4170

Max Act: 3.3566. Min Act: -0.1700

Data Index: 4049968 (Open Web Text)

Max Activating Token Index: 440

Text #5

Max Range: 3.4170. Min Range: -3.4170

Max Act: 3.3521. Min Act: -0.1700

Data Index: 7685590 (Open Web Text)

Max Activating Token Index: 33

Text #6

Max Range: 3.4170. Min Range: -3.4170

Max Act: 3.3189. Min Act: -0.1700

Data Index: 8696530 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.4170. Min Range: -3.4170

Max Act: 3.3100. Min Act: -0.1700

Data Index: 5742508 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 3.4170. Min Range: -3.4170

Max Act: 3.2988. Min Act: -0.1700

Data Index: 6853094 (Open Web Text)

Max Activating Token Index: 102

Text #9

Max Range: 3.4170. Min Range: -3.4170

Max Act: 3.3087. Min Act: -0.1700

Data Index: 3178388 (Open Web Text)

Max Activating Token Index: 142

Text #10

Max Range: 3.4170. Min Range: -3.4170

Max Act: 3.2719. Min Act: -0.1700

Data Index: 3903578 (Open Web Text)

Max Activating Token Index: 41

Text #11

Max Range: 3.4170. Min Range: -3.4170

Max Act: 3.2610. Min Act: -0.1700

Data Index: 8153471 (Open Web Text)

Max Activating Token Index: 59

Text #12

Max Range: 3.4170. Min Range: -3.4170

Max Act: 3.2460. Min Act: -0.1700

Data Index: 2239968 (Open Web Text)

Max Activating Token Index: 925

Text #13

Max Range: 3.4170. Min Range: -3.4170

Max Act: 3.2414. Min Act: -0.1700

Data Index: 4946623 (Open Web Text)

Max Activating Token Index: 239

Text #14

Max Range: 3.4170. Min Range: -3.4170

Max Act: 3.2540. Min Act: -0.1700

Data Index: 2185032 (Open Web Text)

Max Activating Token Index: 79

Text #15

Max Range: 3.4170. Min Range: -3.4170

Max Act: 3.2608. Min Act: -0.1700

Data Index: 2515354 (Open Web Text)

Max Activating Token Index: 173

Text #16

Max Range: 3.4170. Min Range: -3.4170

Max Act: 3.2290. Min Act: -0.1700

Data Index: 2515355 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.4170. Min Range: -3.4170

Max Act: 3.2219. Min Act: -0.1700

Data Index: 2185047 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 3.4170. Min Range: -3.4170

Max Act: 3.2369. Min Act: -0.1700

Data Index: 1054452 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.4170. Min Range: -3.4170

Max Act: 3.2369. Min Act: -0.1700

Data Index: 2868965 (Open Web Text)

Max Activating Token Index: 4