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

Dataset: Open Web Text

Neuron 168 in Layer 6

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: 4.3584. Min Range: -4.3584

Max Act: 4.3584. Min Act: -0.1700

Data Index: 1164936 (Open Web Text)

Max Activating Token Index: 609

Text #1

Max Range: 4.3584. Min Range: -4.3584

Max Act: 4.2777. Min Act: -0.1700

Data Index: 6143421 (Open Web Text)

Max Activating Token Index: 401

Text #2

Max Range: 4.3584. Min Range: -4.3584

Max Act: 4.2303. Min Act: -0.1700

Data Index: 3709970 (Open Web Text)

Max Activating Token Index: 483

Text #3

Max Range: 4.3584. Min Range: -4.3584

Max Act: 4.2252. Min Act: -0.1700

Data Index: 1624256 (Open Web Text)

Max Activating Token Index: 695

Text #4

Max Range: 4.3584. Min Range: -4.3584

Max Act: 4.2100. Min Act: -0.1700

Data Index: 7754957 (Open Web Text)

Max Activating Token Index: 666

Text #5

Max Range: 4.3584. Min Range: -4.3584

Max Act: 4.1947. Min Act: -0.1700

Data Index: 4051529 (Open Web Text)

Max Activating Token Index: 516

Text #6

Max Range: 4.3584. Min Range: -4.3584

Max Act: 4.1803. Min Act: -0.1700

Data Index: 4274043 (Open Web Text)

Max Activating Token Index: 329

Text #7

Max Range: 4.3584. Min Range: -4.3584

Max Act: 4.1619. Min Act: -0.1700

Data Index: 5699591 (Open Web Text)

Max Activating Token Index: 566

Text #8

Max Range: 4.3584. Min Range: -4.3584

Max Act: 4.1524. Min Act: -0.1700

Data Index: 1862509 (Open Web Text)

Max Activating Token Index: 665

Text #9

Max Range: 4.3584. Min Range: -4.3584

Max Act: 4.1499. Min Act: -0.1700

Data Index: 2460064 (Open Web Text)

Max Activating Token Index: 390

Text #10

Max Range: 4.3584. Min Range: -4.3584

Max Act: 4.1557. Min Act: -0.1700

Data Index: 7227922 (Open Web Text)

Max Activating Token Index: 565

Text #11

Max Range: 4.3584. Min Range: -4.3584

Max Act: 4.1557. Min Act: -0.1700

Data Index: 3062634 (Open Web Text)

Max Activating Token Index: 811

Text #12

Max Range: 4.3584. Min Range: -4.3584

Max Act: 4.1511. Min Act: -0.1700

Data Index: 6397784 (Open Web Text)

Max Activating Token Index: 570

Text #13

Max Range: 4.3584. Min Range: -4.3584

Max Act: 4.1178. Min Act: -0.1700

Data Index: 3982557 (Open Web Text)

Max Activating Token Index: 978

Text #14

Max Range: 4.3584. Min Range: -4.3584

Max Act: 4.1061. Min Act: -0.1700

Data Index: 6718693 (Open Web Text)

Max Activating Token Index: 885

Text #15

Max Range: 4.3584. Min Range: -4.3584

Max Act: 4.1254. Min Act: -0.1700

Data Index: 5387796 (Open Web Text)

Max Activating Token Index: 249

Text #16

Max Range: 4.3584. Min Range: -4.3584

Max Act: 4.1194. Min Act: -0.1700

Data Index: 3187416 (Open Web Text)

Max Activating Token Index: 469

Text #17

Max Range: 4.3584. Min Range: -4.3584

Max Act: 4.1168. Min Act: -0.1700

Data Index: 6147332 (Open Web Text)

Max Activating Token Index: 986

Text #18

Max Range: 4.3584. Min Range: -4.3584

Max Act: 4.1125. Min Act: -0.1700

Data Index: 3288675 (Open Web Text)

Max Activating Token Index: 194

Text #19

Max Range: 4.3584. Min Range: -4.3584

Max Act: 4.1297. Min Act: -0.1700

Data Index: 3565230 (Open Web Text)

Max Activating Token Index: 252