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

Dataset: Open Web Text

Neuron 1367 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: 1.4777. Min Range: -1.4777

Max Act: 1.4777. Min Act: -0.1700

Data Index: 5824231 (Open Web Text)

Max Activating Token Index: 753

Text #1

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.4741. Min Act: -0.1700

Data Index: 73804 (Open Web Text)

Max Activating Token Index: 815

Text #2

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.4702. Min Act: -0.1700

Data Index: 6439799 (Open Web Text)

Max Activating Token Index: 507

Text #3

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.4598. Min Act: -0.1700

Data Index: 2878445 (Open Web Text)

Max Activating Token Index: 137

Text #4

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.4445. Min Act: -0.1700

Data Index: 22398 (Open Web Text)

Max Activating Token Index: 37

Text #5

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.4448. Min Act: -0.1700

Data Index: 5178433 (Open Web Text)

Max Activating Token Index: 650

Text #6

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.4173. Min Act: -0.1700

Data Index: 4876122 (Open Web Text)

Max Activating Token Index: 615

Text #7

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.4049. Min Act: -0.1700

Data Index: 8655910 (Open Web Text)

Max Activating Token Index: 838

Text #8

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.4213. Min Act: -0.1700

Data Index: 1987264 (Open Web Text)

Max Activating Token Index: 726

Text #9

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.4164. Min Act: -0.1700

Data Index: 2187386 (Open Web Text)

Max Activating Token Index: 411

Text #10

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.4136. Min Act: -0.1700

Data Index: 8363147 (Open Web Text)

Max Activating Token Index: 657

Text #11

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.4145. Min Act: -0.1700

Data Index: 7518784 (Open Web Text)

Max Activating Token Index: 392

Text #12

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.4105. Min Act: -0.1700

Data Index: 4399795 (Open Web Text)

Max Activating Token Index: 537

Text #13

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.4011. Min Act: -0.1700

Data Index: 6008186 (Open Web Text)

Max Activating Token Index: 516

Text #14

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.4155. Min Act: -0.1700

Data Index: 1577749 (Open Web Text)

Max Activating Token Index: 649

Text #15

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.4038. Min Act: -0.1700

Data Index: 1434416 (Open Web Text)

Max Activating Token Index: 796

Text #16

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.4150. Min Act: -0.1700

Data Index: 4208615 (Open Web Text)

Max Activating Token Index: 290

Text #17

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.4067. Min Act: -0.1700

Data Index: 7461484 (Open Web Text)

Max Activating Token Index: 544

Text #18

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.4024. Min Act: -0.1700

Data Index: 8436875 (Open Web Text)

Max Activating Token Index: 422

Text #19

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.3948. Min Act: -0.1700

Data Index: 8539825 (Open Web Text)

Max Activating Token Index: 923