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

Dataset: Open Web Text

Neuron 1784 in Layer 6

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: 3.3168. Min Range: -3.3168

Max Act: 3.3168. Min Act: -0.1700

Data Index: 6919976 (Open Web Text)

Max Activating Token Index: 138

Text #1

Max Range: 3.3168. Min Range: -3.3168

Max Act: 3.2627. Min Act: -0.1700

Data Index: 8483031 (Open Web Text)

Max Activating Token Index: 615

Text #2

Max Range: 3.3168. Min Range: -3.3168

Max Act: 3.2126. Min Act: -0.1700

Data Index: 591909 (Open Web Text)

Max Activating Token Index: 31

Text #3

Max Range: 3.3168. Min Range: -3.3168

Max Act: 3.2070. Min Act: -0.1700

Data Index: 2469707 (Open Web Text)

Max Activating Token Index: 275

Text #4

Max Range: 3.3168. Min Range: -3.3168

Max Act: 3.1883. Min Act: -0.1700

Data Index: 84149 (Open Web Text)

Max Activating Token Index: 506

Text #5

Max Range: 3.3168. Min Range: -3.3168

Max Act: 3.1782. Min Act: -0.1700

Data Index: 1608508 (Open Web Text)

Max Activating Token Index: 764

Text #6

Max Range: 3.3168. Min Range: -3.3168

Max Act: 3.1528. Min Act: -0.1700

Data Index: 5856757 (Open Web Text)

Max Activating Token Index: 513

Text #7

Max Range: 3.3168. Min Range: -3.3168

Max Act: 3.1481. Min Act: -0.1700

Data Index: 8215179 (Open Web Text)

Max Activating Token Index: 855

Text #8

Max Range: 3.3168. Min Range: -3.3168

Max Act: 3.1486. Min Act: -0.1700

Data Index: 1852682 (Open Web Text)

Max Activating Token Index: 288

Text #9

Max Range: 3.3168. Min Range: -3.3168

Max Act: 3.1127. Min Act: -0.1700

Data Index: 5151163 (Open Web Text)

Max Activating Token Index: 108

Text #10

Max Range: 3.3168. Min Range: -3.3168

Max Act: 3.1418. Min Act: -0.1700

Data Index: 7579192 (Open Web Text)

Max Activating Token Index: 349

Text #11

Max Range: 3.3168. Min Range: -3.3168

Max Act: 3.1003. Min Act: -0.1700

Data Index: 6467091 (Open Web Text)

Max Activating Token Index: 1011

Text #12

Max Range: 3.3168. Min Range: -3.3168

Max Act: 3.0946. Min Act: -0.1700

Data Index: 4485996 (Open Web Text)

Max Activating Token Index: 554

Text #13

Max Range: 3.3168. Min Range: -3.3168

Max Act: 3.0669. Min Act: -0.1700

Data Index: 782741 (Open Web Text)

Max Activating Token Index: 1000

Text #14

Max Range: 3.3168. Min Range: -3.3168

Max Act: 3.0666. Min Act: -0.1700

Data Index: 1904229 (Open Web Text)

Max Activating Token Index: 1020

Text #15

Max Range: 3.3168. Min Range: -3.3168

Max Act: 3.0564. Min Act: -0.1700

Data Index: 740397 (Open Web Text)

Max Activating Token Index: 337

Text #16

Max Range: 3.3168. Min Range: -3.3168

Max Act: 3.0486. Min Act: -0.1700

Data Index: 8489143 (Open Web Text)

Max Activating Token Index: 593

Text #17

Max Range: 3.3168. Min Range: -3.3168

Max Act: 3.0880. Min Act: -0.1700

Data Index: 839499 (Open Web Text)

Max Activating Token Index: 504

Text #18

Max Range: 3.3168. Min Range: -3.3168

Max Act: 3.0460. Min Act: -0.1700

Data Index: 7317105 (Open Web Text)

Max Activating Token Index: 694

Text #19

Max Range: 3.3168. Min Range: -3.3168

Max Act: 3.0232. Min Act: -0.1700

Data Index: 5805247 (Open Web Text)

Max Activating Token Index: 872