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

Dataset: Open Web Text

Neuron 911 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: 3.4399. Min Range: -3.4399

Max Act: 3.4399. Min Act: -0.1700

Data Index: 3171187 (Open Web Text)

Max Activating Token Index: 397

Text #1

Max Range: 3.4399. Min Range: -3.4399

Max Act: 3.2145. Min Act: -0.1700

Data Index: 6038391 (Open Web Text)

Max Activating Token Index: 662

Text #2

Max Range: 3.4399. Min Range: -3.4399

Max Act: 3.2304. Min Act: -0.1700

Data Index: 7222028 (Open Web Text)

Max Activating Token Index: 976

Text #3

Max Range: 3.4399. Min Range: -3.4399

Max Act: 3.1990. Min Act: -0.1700

Data Index: 5485037 (Open Web Text)

Max Activating Token Index: 125

Text #4

Max Range: 3.4399. Min Range: -3.4399

Max Act: 3.1945. Min Act: -0.1700

Data Index: 6159975 (Open Web Text)

Max Activating Token Index: 665

Text #5

Max Range: 3.4399. Min Range: -3.4399

Max Act: 3.1651. Min Act: -0.1700

Data Index: 7800068 (Open Web Text)

Max Activating Token Index: 400

Text #6

Max Range: 3.4399. Min Range: -3.4399

Max Act: 3.1791. Min Act: -0.1700

Data Index: 6037595 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.4399. Min Range: -3.4399

Max Act: 3.1415. Min Act: -0.1700

Data Index: 685380 (Open Web Text)

Max Activating Token Index: 647

Text #8

Max Range: 3.4399. Min Range: -3.4399

Max Act: 3.1549. Min Act: -0.1700

Data Index: 5462207 (Open Web Text)

Max Activating Token Index: 697

Text #9

Max Range: 3.4399. Min Range: -3.4399

Max Act: 3.1393. Min Act: -0.1700

Data Index: 1850829 (Open Web Text)

Max Activating Token Index: 470

Text #10

Max Range: 3.4399. Min Range: -3.4399

Max Act: 3.1366. Min Act: -0.1700

Data Index: 4950897 (Open Web Text)

Max Activating Token Index: 990

Text #11

Max Range: 3.4399. Min Range: -3.4399

Max Act: 3.1170. Min Act: -0.1700

Data Index: 3234024 (Open Web Text)

Max Activating Token Index: 714

Text #12

Max Range: 3.4399. Min Range: -3.4399

Max Act: 3.1226. Min Act: -0.1700

Data Index: 6306885 (Open Web Text)

Max Activating Token Index: 624

Text #13

Max Range: 3.4399. Min Range: -3.4399

Max Act: 3.1221. Min Act: -0.1700

Data Index: 6499411 (Open Web Text)

Max Activating Token Index: 606

Text #14

Max Range: 3.4399. Min Range: -3.4399

Max Act: 3.0871. Min Act: -0.1700

Data Index: 5794126 (Open Web Text)

Max Activating Token Index: 665

Text #15

Max Range: 3.4399. Min Range: -3.4399

Max Act: 3.1080. Min Act: -0.1700

Data Index: 1570284 (Open Web Text)

Max Activating Token Index: 555

Text #16

Max Range: 3.4399. Min Range: -3.4399

Max Act: 3.0609. Min Act: -0.1700

Data Index: 5286567 (Open Web Text)

Max Activating Token Index: 309

Text #17

Max Range: 3.4399. Min Range: -3.4399

Max Act: 3.0651. Min Act: -0.1700

Data Index: 4551030 (Open Web Text)

Max Activating Token Index: 618

Text #18

Max Range: 3.4399. Min Range: -3.4399

Max Act: 3.0601. Min Act: -0.1700

Data Index: 2804222 (Open Web Text)

Max Activating Token Index: 60

Text #19

Max Range: 3.4399. Min Range: -3.4399

Max Act: 3.0258. Min Act: -0.1700

Data Index: 7345370 (Open Web Text)

Max Activating Token Index: 1016