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

Dataset: Open Web Text

Neuron 484 in Layer 1

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: 6.4035. Min Range: -6.4035

Max Act: 6.4035. Min Act: -0.1700

Data Index: 8104999 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 6.4035. Min Range: -6.4035

Max Act: 6.3622. Min Act: -0.1700

Data Index: 647635 (Open Web Text)

Max Activating Token Index: 91

Text #2

Max Range: 6.4035. Min Range: -6.4035

Max Act: 6.3337. Min Act: -0.1700

Data Index: 4352674 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 6.4035. Min Range: -6.4035

Max Act: 6.3231. Min Act: -0.1700

Data Index: 4777712 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 6.4035. Min Range: -6.4035

Max Act: 6.1944. Min Act: -0.1700

Data Index: 1566040 (Open Web Text)

Max Activating Token Index: 546

Text #5

Max Range: 6.4035. Min Range: -6.4035

Max Act: 6.1368. Min Act: -0.1700

Data Index: 2644263 (Open Web Text)

Max Activating Token Index: 218

Text #6

Max Range: 6.4035. Min Range: -6.4035

Max Act: 6.1407. Min Act: -0.1700

Data Index: 2106759 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 6.4035. Min Range: -6.4035

Max Act: 6.1104. Min Act: -0.1700

Data Index: 6112199 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 6.4035. Min Range: -6.4035

Max Act: 6.0618. Min Act: -0.1700

Data Index: 1974740 (Open Web Text)

Max Activating Token Index: 21

Text #9

Max Range: 6.4035. Min Range: -6.4035

Max Act: 6.0559. Min Act: -0.1700

Data Index: 5329728 (Open Web Text)

Max Activating Token Index: 465

Text #10

Max Range: 6.4035. Min Range: -6.4035

Max Act: 6.0512. Min Act: -0.1700

Data Index: 3897351 (Open Web Text)

Max Activating Token Index: 117

Text #11

Max Range: 6.4035. Min Range: -6.4035

Max Act: 6.0441. Min Act: -0.1700

Data Index: 3809529 (Open Web Text)

Max Activating Token Index: 543

Text #12

Max Range: 6.4035. Min Range: -6.4035

Max Act: 6.0514. Min Act: -0.1700

Data Index: 8488583 (Open Web Text)

Max Activating Token Index: 115

Text #13

Max Range: 6.4035. Min Range: -6.4035

Max Act: 6.0678. Min Act: -0.1700

Data Index: 1066018 (Open Web Text)

Max Activating Token Index: 94

Text #14

Max Range: 6.4035. Min Range: -6.4035

Max Act: 6.0358. Min Act: -0.1700

Data Index: 5766965 (Open Web Text)

Max Activating Token Index: 146

Text #15

Max Range: 6.4035. Min Range: -6.4035

Max Act: 6.0342. Min Act: -0.1700

Data Index: 3080674 (Open Web Text)

Max Activating Token Index: 158

Text #16

Max Range: 6.4035. Min Range: -6.4035

Max Act: 6.0382. Min Act: -0.1700

Data Index: 2820563 (Open Web Text)

Max Activating Token Index: 166

Text #17

Max Range: 6.4035. Min Range: -6.4035

Max Act: 6.0517. Min Act: -0.1700

Data Index: 6213167 (Open Web Text)

Max Activating Token Index: 39

Text #18

Max Range: 6.4035. Min Range: -6.4035

Max Act: 6.0341. Min Act: -0.1700

Data Index: 2258732 (Open Web Text)

Max Activating Token Index: 953

Text #19

Max Range: 6.4035. Min Range: -6.4035

Max Act: 5.9959. Min Act: -0.1700

Data Index: 578336 (Open Web Text)

Max Activating Token Index: 84