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

Dataset: Open Web Text

Neuron 3060 in Layer 2

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: 5.1650. Min Range: -5.1650

Max Act: 5.1650. Min Act: -0.1700

Data Index: 2597700 (Open Web Text)

Max Activating Token Index: 118

Text #1

Max Range: 5.1650. Min Range: -5.1650

Max Act: 5.1016. Min Act: -0.1700

Data Index: 6523266 (Open Web Text)

Max Activating Token Index: 58

Text #2

Max Range: 5.1650. Min Range: -5.1650

Max Act: 5.1142. Min Act: -0.1700

Data Index: 8808577 (Open Web Text)

Max Activating Token Index: 308

Text #3

Max Range: 5.1650. Min Range: -5.1650

Max Act: 5.1191. Min Act: -0.1700

Data Index: 4204809 (Open Web Text)

Max Activating Token Index: 886

Text #4

Max Range: 5.1650. Min Range: -5.1650

Max Act: 5.1187. Min Act: -0.1700

Data Index: 1591389 (Open Web Text)

Max Activating Token Index: 332

Text #5

Max Range: 5.1650. Min Range: -5.1650

Max Act: 5.1197. Min Act: -0.1700

Data Index: 2866492 (Open Web Text)

Max Activating Token Index: 488

Text #6

Max Range: 5.1650. Min Range: -5.1650

Max Act: 5.1341. Min Act: -0.1700

Data Index: 6775870 (Open Web Text)

Max Activating Token Index: 228

Text #7

Max Range: 5.1650. Min Range: -5.1650

Max Act: 5.1167. Min Act: -0.1700

Data Index: 1314095 (Open Web Text)

Max Activating Token Index: 297

Text #8

Max Range: 5.1650. Min Range: -5.1650

Max Act: 5.1240. Min Act: -0.1700

Data Index: 7729787 (Open Web Text)

Max Activating Token Index: 408

Text #9

Max Range: 5.1650. Min Range: -5.1650

Max Act: 5.0806. Min Act: -0.1700

Data Index: 3443053 (Open Web Text)

Max Activating Token Index: 654

Text #10

Max Range: 5.1650. Min Range: -5.1650

Max Act: 5.0812. Min Act: -0.1700

Data Index: 3332038 (Open Web Text)

Max Activating Token Index: 190

Text #11

Max Range: 5.1650. Min Range: -5.1650

Max Act: 5.1105. Min Act: -0.1700

Data Index: 792980 (Open Web Text)

Max Activating Token Index: 208

Text #12

Max Range: 5.1650. Min Range: -5.1650

Max Act: 5.1015. Min Act: -0.1700

Data Index: 437251 (Open Web Text)

Max Activating Token Index: 576

Text #13

Max Range: 5.1650. Min Range: -5.1650

Max Act: 5.1145. Min Act: -0.1700

Data Index: 3920494 (Open Web Text)

Max Activating Token Index: 448

Text #14

Max Range: 5.1650. Min Range: -5.1650

Max Act: 5.0851. Min Act: -0.1700

Data Index: 7263612 (Open Web Text)

Max Activating Token Index: 717

Text #15

Max Range: 5.1650. Min Range: -5.1650

Max Act: 5.0745. Min Act: -0.1700

Data Index: 7042621 (Open Web Text)

Max Activating Token Index: 76

Text #16

Max Range: 5.1650. Min Range: -5.1650

Max Act: 5.0895. Min Act: -0.1700

Data Index: 6763133 (Open Web Text)

Max Activating Token Index: 96

Text #17

Max Range: 5.1650. Min Range: -5.1650

Max Act: 5.0958. Min Act: -0.1700

Data Index: 872906 (Open Web Text)

Max Activating Token Index: 142

Text #18

Max Range: 5.1650. Min Range: -5.1650

Max Act: 5.0853. Min Act: -0.1700

Data Index: 3853959 (Open Web Text)

Max Activating Token Index: 445

Text #19

Max Range: 5.1650. Min Range: -5.1650

Max Act: 5.0838. Min Act: -0.1700

Data Index: 6656930 (Open Web Text)

Max Activating Token Index: 100