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

Dataset: Open Web Text

Neuron 1858 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: 3.8129. Min Range: -3.8129

Max Act: 3.8129. Min Act: -0.1700

Data Index: 3814677 (Open Web Text)

Max Activating Token Index: 515

Text #1

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.8046. Min Act: -0.1700

Data Index: 7317107 (Open Web Text)

Max Activating Token Index: 824

Text #2

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.8049. Min Act: -0.1700

Data Index: 8090247 (Open Web Text)

Max Activating Token Index: 996

Text #3

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.7480. Min Act: -0.1700

Data Index: 2363631 (Open Web Text)

Max Activating Token Index: 548

Text #4

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.7764. Min Act: -0.1700

Data Index: 2221897 (Open Web Text)

Max Activating Token Index: 1020

Text #5

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.7739. Min Act: -0.1700

Data Index: 5664014 (Open Web Text)

Max Activating Token Index: 1017

Text #6

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.7364. Min Act: -0.1700

Data Index: 3434735 (Open Web Text)

Max Activating Token Index: 742

Text #7

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.7316. Min Act: -0.1700

Data Index: 2646453 (Open Web Text)

Max Activating Token Index: 242

Text #8

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.7435. Min Act: -0.1700

Data Index: 6353025 (Open Web Text)

Max Activating Token Index: 280

Text #9

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.7233. Min Act: -0.1700

Data Index: 5218064 (Open Web Text)

Max Activating Token Index: 917

Text #10

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.7298. Min Act: -0.1700

Data Index: 2283636 (Open Web Text)

Max Activating Token Index: 433

Text #11

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.7438. Min Act: -0.1700

Data Index: 2236433 (Open Web Text)

Max Activating Token Index: 545

Text #12

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.7407. Min Act: -0.1700

Data Index: 99876 (Open Web Text)

Max Activating Token Index: 774

Text #13

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.7518. Min Act: -0.1700

Data Index: 2166109 (Open Web Text)

Max Activating Token Index: 299

Text #14

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.7438. Min Act: -0.1700

Data Index: 5175588 (Open Web Text)

Max Activating Token Index: 731

Text #15

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.7407. Min Act: -0.1700

Data Index: 4891962 (Open Web Text)

Max Activating Token Index: 904

Text #16

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.7461. Min Act: -0.1700

Data Index: 406962 (Open Web Text)

Max Activating Token Index: 980

Text #17

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.7275. Min Act: -0.1700

Data Index: 2905115 (Open Web Text)

Max Activating Token Index: 504

Text #18

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.6984. Min Act: -0.1700

Data Index: 2916109 (Open Web Text)

Max Activating Token Index: 545

Text #19

Max Range: 3.8129. Min Range: -3.8129

Max Act: 3.7289. Min Act: -0.1700

Data Index: 1784503 (Open Web Text)

Max Activating Token Index: 418