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

Dataset: Open Web Text

Neuron 1155 in Layer 4

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: 3.9611. Min Range: -3.9611

Max Act: 3.9611. Min Act: -0.1700

Data Index: 2277037 (Open Web Text)

Max Activating Token Index: 324

Text #1

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.8433. Min Act: -0.1700

Data Index: 8124416 (Open Web Text)

Max Activating Token Index: 851

Text #2

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.8094. Min Act: -0.1700

Data Index: 6210894 (Open Web Text)

Max Activating Token Index: 953

Text #3

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.8295. Min Act: -0.1700

Data Index: 1587633 (Open Web Text)

Max Activating Token Index: 389

Text #4

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.8141. Min Act: -0.1700

Data Index: 2048218 (Open Web Text)

Max Activating Token Index: 829

Text #5

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.8169. Min Act: -0.1700

Data Index: 1952402 (Open Web Text)

Max Activating Token Index: 243

Text #6

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.7845. Min Act: -0.1700

Data Index: 6753744 (Open Web Text)

Max Activating Token Index: 962

Text #7

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.8143. Min Act: -0.1700

Data Index: 2653984 (Open Web Text)

Max Activating Token Index: 112

Text #8

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.7394. Min Act: -0.1700

Data Index: 1899758 (Open Web Text)

Max Activating Token Index: 463

Text #9

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.7440. Min Act: -0.1700

Data Index: 4928794 (Open Web Text)

Max Activating Token Index: 692

Text #10

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.7375. Min Act: -0.1700

Data Index: 5611739 (Open Web Text)

Max Activating Token Index: 257

Text #11

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.7232. Min Act: -0.1700

Data Index: 2310407 (Open Web Text)

Max Activating Token Index: 422

Text #12

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.6938. Min Act: -0.1700

Data Index: 5708600 (Open Web Text)

Max Activating Token Index: 866

Text #13

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.7117. Min Act: -0.1700

Data Index: 2034670 (Open Web Text)

Max Activating Token Index: 671

Text #14

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.6894. Min Act: -0.1700

Data Index: 3530202 (Open Web Text)

Max Activating Token Index: 297

Text #15

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.7142. Min Act: -0.1700

Data Index: 5555004 (Open Web Text)

Max Activating Token Index: 636

Text #16

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.6821. Min Act: -0.1700

Data Index: 279250 (Open Web Text)

Max Activating Token Index: 80

Text #17

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.6567. Min Act: -0.1700

Data Index: 4161529 (Open Web Text)

Max Activating Token Index: 140

Text #18

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.6950. Min Act: -0.1700

Data Index: 3697205 (Open Web Text)

Max Activating Token Index: 299

Text #19

Max Range: 3.9611. Min Range: -3.9611

Max Act: 3.6876. Min Act: -0.1700

Data Index: 1514165 (Open Web Text)

Max Activating Token Index: 319