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

Dataset: Open Web Text

Neuron 1899 in Layer 0

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: 5.6327. Min Range: -5.6327

Max Act: 5.6327. Min Act: -0.1700

Data Index: 5682385 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.6327. Min Range: -5.6327

Max Act: 5.5942. Min Act: -0.1700

Data Index: 1571823 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.6327. Min Range: -5.6327

Max Act: 5.5994. Min Act: -0.1700

Data Index: 3309111 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 5.6327. Min Range: -5.6327

Max Act: 5.5444. Min Act: -0.1700

Data Index: 1455341 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 5.6327. Min Range: -5.6327

Max Act: 5.5580. Min Act: -0.1700

Data Index: 2996964 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 5.6327. Min Range: -5.6327

Max Act: 5.5210. Min Act: -0.1700

Data Index: 7053156 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 5.6327. Min Range: -5.6327

Max Act: 5.5256. Min Act: -0.1699

Data Index: 7010668 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 5.6327. Min Range: -5.6327

Max Act: 5.5378. Min Act: -0.1700

Data Index: 5766567 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 5.6327. Min Range: -5.6327

Max Act: 5.5306. Min Act: -0.1700

Data Index: 5562388 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 5.6327. Min Range: -5.6327

Max Act: 5.5205. Min Act: -0.1699

Data Index: 4963204 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 5.6327. Min Range: -5.6327

Max Act: 5.5427. Min Act: -0.1700

Data Index: 4427841 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 5.6327. Min Range: -5.6327

Max Act: 5.5281. Min Act: -0.1698

Data Index: 4250219 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.6327. Min Range: -5.6327

Max Act: 5.5101. Min Act: -0.1700

Data Index: 2652944 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 5.6327. Min Range: -5.6327

Max Act: 5.5325. Min Act: -0.1700

Data Index: 4042914 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 5.6327. Min Range: -5.6327

Max Act: 5.5156. Min Act: -0.1700

Data Index: 3776876 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.6327. Min Range: -5.6327

Max Act: 5.5374. Min Act: -0.1700

Data Index: 3632603 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 5.6327. Min Range: -5.6327

Max Act: 5.5290. Min Act: -0.1692

Data Index: 3486517 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 5.6327. Min Range: -5.6327

Max Act: 5.5231. Min Act: -0.1700

Data Index: 3330979 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 5.6327. Min Range: -5.6327

Max Act: 5.5338. Min Act: -0.1699

Data Index: 2473635 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 5.6327. Min Range: -5.6327

Max Act: 5.5132. Min Act: -0.1700

Data Index: 2250648 (Open Web Text)

Max Activating Token Index: 4