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

Dataset: Open Web Text

Neuron 1869 in Layer 4

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: 4.1079. Min Range: -4.1079

Max Act: 4.1079. Min Act: -0.1700

Data Index: 5117581 (Open Web Text)

Max Activating Token Index: 220

Text #1

Max Range: 4.1079. Min Range: -4.1079

Max Act: 4.0563. Min Act: -0.1700

Data Index: 4084527 (Open Web Text)

Max Activating Token Index: 180

Text #2

Max Range: 4.1079. Min Range: -4.1079

Max Act: 4.0633. Min Act: -0.1700

Data Index: 6845904 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 4.1079. Min Range: -4.1079

Max Act: 4.0060. Min Act: -0.1700

Data Index: 3691265 (Open Web Text)

Max Activating Token Index: 390

Text #4

Max Range: 4.1079. Min Range: -4.1079

Max Act: 4.0531. Min Act: -0.1700

Data Index: 3790426 (Open Web Text)

Max Activating Token Index: 211

Text #5

Max Range: 4.1079. Min Range: -4.1079

Max Act: 4.0437. Min Act: -0.1700

Data Index: 1429117 (Open Web Text)

Max Activating Token Index: 294

Text #6

Max Range: 4.1079. Min Range: -4.1079

Max Act: 4.0405. Min Act: -0.1700

Data Index: 7506266 (Open Web Text)

Max Activating Token Index: 507

Text #7

Max Range: 4.1079. Min Range: -4.1079

Max Act: 3.9935. Min Act: -0.1700

Data Index: 5033824 (Open Web Text)

Max Activating Token Index: 148

Text #8

Max Range: 4.1079. Min Range: -4.1079

Max Act: 3.9508. Min Act: -0.1700

Data Index: 2510656 (Open Web Text)

Max Activating Token Index: 613

Text #9

Max Range: 4.1079. Min Range: -4.1079

Max Act: 3.9848. Min Act: -0.1700

Data Index: 6928856 (Open Web Text)

Max Activating Token Index: 35

Text #10

Max Range: 4.1079. Min Range: -4.1079

Max Act: 3.9845. Min Act: -0.1700

Data Index: 1656893 (Open Web Text)

Max Activating Token Index: 613

Text #11

Max Range: 4.1079. Min Range: -4.1079

Max Act: 3.9863. Min Act: -0.1700

Data Index: 8579332 (Open Web Text)

Max Activating Token Index: 237

Text #12

Max Range: 4.1079. Min Range: -4.1079

Max Act: 3.9272. Min Act: -0.1700

Data Index: 5105232 (Open Web Text)

Max Activating Token Index: 32

Text #13

Max Range: 4.1079. Min Range: -4.1079

Max Act: 3.9469. Min Act: -0.1700

Data Index: 857761 (Open Web Text)

Max Activating Token Index: 140

Text #14

Max Range: 4.1079. Min Range: -4.1079

Max Act: 3.9661. Min Act: -0.1700

Data Index: 2222513 (Open Web Text)

Max Activating Token Index: 17

Text #15

Max Range: 4.1079. Min Range: -4.1079

Max Act: 3.9526. Min Act: -0.1700

Data Index: 7744064 (Open Web Text)

Max Activating Token Index: 88

Text #16

Max Range: 4.1079. Min Range: -4.1079

Max Act: 3.9311. Min Act: -0.1700

Data Index: 3764518 (Open Web Text)

Max Activating Token Index: 116

Text #17

Max Range: 4.1079. Min Range: -4.1079

Max Act: 3.9134. Min Act: -0.1700

Data Index: 6977536 (Open Web Text)

Max Activating Token Index: 937

Text #18

Max Range: 4.1079. Min Range: -4.1079

Max Act: 3.9099. Min Act: -0.1700

Data Index: 2205040 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 4.1079. Min Range: -4.1079

Max Act: 3.8880. Min Act: -0.1700

Data Index: 8570829 (Open Web Text)

Max Activating Token Index: 990