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

Dataset: Open Web Text

Neuron 390 in Layer 5

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: 6.6046. Min Range: -6.6046

Max Act: 6.6046. Min Act: -0.1700

Data Index: 5629752 (Open Web Text)

Max Activating Token Index: 387

Text #1

Max Range: 6.6046. Min Range: -6.6046

Max Act: 6.4314. Min Act: -0.1700

Data Index: 7459287 (Open Web Text)

Max Activating Token Index: 530

Text #2

Max Range: 6.6046. Min Range: -6.6046

Max Act: 6.2039. Min Act: -0.1700

Data Index: 4010691 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 6.6046. Min Range: -6.6046

Max Act: 6.2145. Min Act: -0.1700

Data Index: 1457045 (Open Web Text)

Max Activating Token Index: 573

Text #4

Max Range: 6.6046. Min Range: -6.6046

Max Act: 6.1782. Min Act: -0.1700

Data Index: 4083049 (Open Web Text)

Max Activating Token Index: 339

Text #5

Max Range: 6.6046. Min Range: -6.6046

Max Act: 6.1941. Min Act: -0.1700

Data Index: 7160255 (Open Web Text)

Max Activating Token Index: 511

Text #6

Max Range: 6.6046. Min Range: -6.6046

Max Act: 6.1984. Min Act: -0.1700

Data Index: 7231993 (Open Web Text)

Max Activating Token Index: 77

Text #7

Max Range: 6.6046. Min Range: -6.6046

Max Act: 6.1714. Min Act: -0.1700

Data Index: 8111543 (Open Web Text)

Max Activating Token Index: 740

Text #8

Max Range: 6.6046. Min Range: -6.6046

Max Act: 6.2212. Min Act: -0.1700

Data Index: 1436034 (Open Web Text)

Max Activating Token Index: 390

Text #9

Max Range: 6.6046. Min Range: -6.6046

Max Act: 6.1636. Min Act: -0.1700

Data Index: 4004552 (Open Web Text)

Max Activating Token Index: 333

Text #10

Max Range: 6.6046. Min Range: -6.6046

Max Act: 6.1977. Min Act: -0.1700

Data Index: 5360543 (Open Web Text)

Max Activating Token Index: 304

Text #11

Max Range: 6.6046. Min Range: -6.6046

Max Act: 6.1983. Min Act: -0.1700

Data Index: 7919332 (Open Web Text)

Max Activating Token Index: 917

Text #12

Max Range: 6.6046. Min Range: -6.6046

Max Act: 6.1565. Min Act: -0.1700

Data Index: 8389302 (Open Web Text)

Max Activating Token Index: 774

Text #13

Max Range: 6.6046. Min Range: -6.6046

Max Act: 6.1525. Min Act: -0.1700

Data Index: 3941054 (Open Web Text)

Max Activating Token Index: 551

Text #14

Max Range: 6.6046. Min Range: -6.6046

Max Act: 6.1334. Min Act: -0.1700

Data Index: 935239 (Open Web Text)

Max Activating Token Index: 869

Text #15

Max Range: 6.6046. Min Range: -6.6046

Max Act: 6.1486. Min Act: -0.1700

Data Index: 2592245 (Open Web Text)

Max Activating Token Index: 92

Text #16

Max Range: 6.6046. Min Range: -6.6046

Max Act: 6.1340. Min Act: -0.1700

Data Index: 6686138 (Open Web Text)

Max Activating Token Index: 685

Text #17

Max Range: 6.6046. Min Range: -6.6046

Max Act: 6.1598. Min Act: -0.1700

Data Index: 6249778 (Open Web Text)

Max Activating Token Index: 363

Text #18

Max Range: 6.6046. Min Range: -6.6046

Max Act: 6.1450. Min Act: -0.1700

Data Index: 5534300 (Open Web Text)

Max Activating Token Index: 779

Text #19

Max Range: 6.6046. Min Range: -6.6046

Max Act: 6.1524. Min Act: -0.1700

Data Index: 1856045 (Open Web Text)

Max Activating Token Index: 349