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

Dataset: Open Web Text

Neuron 631 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: 3.9286. Min Range: -3.9286

Max Act: 3.8979. Min Act: -0.1700

Data Index: 4356169 (Open Web Text)

Max Activating Token Index: 355

Text #1

Max Range: 3.9286. Min Range: -3.9286

Max Act: 3.9286. Min Act: -0.1700

Data Index: 3686513 (Open Web Text)

Max Activating Token Index: 1014

Text #2

Max Range: 3.9286. Min Range: -3.9286

Max Act: 3.8552. Min Act: -0.1700

Data Index: 7441470 (Open Web Text)

Max Activating Token Index: 946

Text #3

Max Range: 3.9286. Min Range: -3.9286

Max Act: 3.8729. Min Act: -0.1700

Data Index: 2353357 (Open Web Text)

Max Activating Token Index: 683

Text #4

Max Range: 3.9286. Min Range: -3.9286

Max Act: 3.8325. Min Act: -0.1700

Data Index: 2309077 (Open Web Text)

Max Activating Token Index: 885

Text #5

Max Range: 3.9286. Min Range: -3.9286

Max Act: 3.8294. Min Act: -0.1700

Data Index: 1968070 (Open Web Text)

Max Activating Token Index: 476

Text #6

Max Range: 3.9286. Min Range: -3.9286

Max Act: 3.8126. Min Act: -0.1700

Data Index: 1185758 (Open Web Text)

Max Activating Token Index: 784

Text #7

Max Range: 3.9286. Min Range: -3.9286

Max Act: 3.8382. Min Act: -0.1700

Data Index: 6077725 (Open Web Text)

Max Activating Token Index: 953

Text #8

Max Range: 3.9286. Min Range: -3.9286

Max Act: 3.8174. Min Act: -0.1700

Data Index: 6702550 (Open Web Text)

Max Activating Token Index: 821

Text #9

Max Range: 3.9286. Min Range: -3.9286

Max Act: 3.8171. Min Act: -0.1700

Data Index: 6233568 (Open Web Text)

Max Activating Token Index: 713

Text #10

Max Range: 3.9286. Min Range: -3.9286

Max Act: 3.8201. Min Act: -0.1700

Data Index: 6096007 (Open Web Text)

Max Activating Token Index: 872

Text #11

Max Range: 3.9286. Min Range: -3.9286

Max Act: 3.8194. Min Act: -0.1700

Data Index: 7683612 (Open Web Text)

Max Activating Token Index: 923

Text #12

Max Range: 3.9286. Min Range: -3.9286

Max Act: 3.8318. Min Act: -0.1700

Data Index: 8126353 (Open Web Text)

Max Activating Token Index: 758

Text #13

Max Range: 3.9286. Min Range: -3.9286

Max Act: 3.8183. Min Act: -0.1700

Data Index: 5020083 (Open Web Text)

Max Activating Token Index: 636

Text #14

Max Range: 3.9286. Min Range: -3.9286

Max Act: 3.8078. Min Act: -0.1700

Data Index: 8146542 (Open Web Text)

Max Activating Token Index: 348

Text #15

Max Range: 3.9286. Min Range: -3.9286

Max Act: 3.7731. Min Act: -0.1700

Data Index: 1327755 (Open Web Text)

Max Activating Token Index: 1004

Text #16

Max Range: 3.9286. Min Range: -3.9286

Max Act: 3.7769. Min Act: -0.1700

Data Index: 7092556 (Open Web Text)

Max Activating Token Index: 505

Text #17

Max Range: 3.9286. Min Range: -3.9286

Max Act: 3.7966. Min Act: -0.1700

Data Index: 4441299 (Open Web Text)

Max Activating Token Index: 230

Text #18

Max Range: 3.9286. Min Range: -3.9286

Max Act: 3.7666. Min Act: -0.1700

Data Index: 77030 (Open Web Text)

Max Activating Token Index: 800

Text #19

Max Range: 3.9286. Min Range: -3.9286

Max Act: 3.7547. Min Act: -0.1700

Data Index: 5092329 (Open Web Text)

Max Activating Token Index: 776