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

Dataset: Open Web Text

Neuron 512 in Layer 2

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: 4.4340. Min Range: -4.4340

Max Act: 4.4340. Min Act: -0.1700

Data Index: 5767391 (Open Web Text)

Max Activating Token Index: 124

Text #1

Max Range: 4.4340. Min Range: -4.4340

Max Act: 4.3265. Min Act: -0.1700

Data Index: 3230160 (Open Web Text)

Max Activating Token Index: 636

Text #2

Max Range: 4.4340. Min Range: -4.4340

Max Act: 4.3268. Min Act: -0.1700

Data Index: 6030197 (Open Web Text)

Max Activating Token Index: 425

Text #3

Max Range: 4.4340. Min Range: -4.4340

Max Act: 4.3294. Min Act: -0.1700

Data Index: 510651 (Open Web Text)

Max Activating Token Index: 104

Text #4

Max Range: 4.4340. Min Range: -4.4340

Max Act: 4.3210. Min Act: -0.1700

Data Index: 8774485 (Open Web Text)

Max Activating Token Index: 538

Text #5

Max Range: 4.4340. Min Range: -4.4340

Max Act: 4.2784. Min Act: -0.1700

Data Index: 5614025 (Open Web Text)

Max Activating Token Index: 121

Text #6

Max Range: 4.4340. Min Range: -4.4340

Max Act: 4.2839. Min Act: -0.1700

Data Index: 3822433 (Open Web Text)

Max Activating Token Index: 491

Text #7

Max Range: 4.4340. Min Range: -4.4340

Max Act: 4.2626. Min Act: -0.1700

Data Index: 8430838 (Open Web Text)

Max Activating Token Index: 516

Text #8

Max Range: 4.4340. Min Range: -4.4340

Max Act: 4.2534. Min Act: -0.1700

Data Index: 3727931 (Open Web Text)

Max Activating Token Index: 68

Text #9

Max Range: 4.4340. Min Range: -4.4340

Max Act: 4.2115. Min Act: -0.1700

Data Index: 2890750 (Open Web Text)

Max Activating Token Index: 507

Text #10

Max Range: 4.4340. Min Range: -4.4340

Max Act: 4.2273. Min Act: -0.1700

Data Index: 1261561 (Open Web Text)

Max Activating Token Index: 779

Text #11

Max Range: 4.4340. Min Range: -4.4340

Max Act: 4.2271. Min Act: -0.1700

Data Index: 4133658 (Open Web Text)

Max Activating Token Index: 884

Text #12

Max Range: 4.4340. Min Range: -4.4340

Max Act: 4.1779. Min Act: -0.1700

Data Index: 2647669 (Open Web Text)

Max Activating Token Index: 255

Text #13

Max Range: 4.4340. Min Range: -4.4340

Max Act: 4.1776. Min Act: -0.1700

Data Index: 5221488 (Open Web Text)

Max Activating Token Index: 86

Text #14

Max Range: 4.4340. Min Range: -4.4340

Max Act: 4.1938. Min Act: -0.1700

Data Index: 6412888 (Open Web Text)

Max Activating Token Index: 73

Text #15

Max Range: 4.4340. Min Range: -4.4340

Max Act: 4.1799. Min Act: -0.1700

Data Index: 5770308 (Open Web Text)

Max Activating Token Index: 519

Text #16

Max Range: 4.4340. Min Range: -4.4340

Max Act: 4.1935. Min Act: -0.1700

Data Index: 2644315 (Open Web Text)

Max Activating Token Index: 592

Text #17

Max Range: 4.4340. Min Range: -4.4340

Max Act: 4.1862. Min Act: -0.1700

Data Index: 1648447 (Open Web Text)

Max Activating Token Index: 271

Text #18

Max Range: 4.4340. Min Range: -4.4340

Max Act: 4.1643. Min Act: -0.1700

Data Index: 2547141 (Open Web Text)

Max Activating Token Index: 130

Text #19

Max Range: 4.4340. Min Range: -4.4340

Max Act: 4.1508. Min Act: -0.1700

Data Index: 3958476 (Open Web Text)

Max Activating Token Index: 964