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

Dataset: Open Web Text

Neuron 1596 in Layer 0

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: 1.4516. Min Range: -1.4516

Max Act: 1.4489. Min Act: -0.1438

Data Index: 8405813 (Open Web Text)

Max Activating Token Index: 1014

Text #1

Max Range: 1.4516. Min Range: -1.4516

Max Act: 1.4516. Min Act: -0.0990

Data Index: 3726760 (Open Web Text)

Max Activating Token Index: 69

Text #2

Max Range: 1.4516. Min Range: -1.4516

Max Act: 1.4484. Min Act: -0.0539

Data Index: 661928 (Open Web Text)

Max Activating Token Index: 1006

Text #3

Max Range: 1.4516. Min Range: -1.4516

Max Act: 1.4498. Min Act: -0.1283

Data Index: 6617044 (Open Web Text)

Max Activating Token Index: 128

Text #4

Max Range: 1.4516. Min Range: -1.4516

Max Act: 1.4473. Min Act: -0.0038

Data Index: 2045129 (Open Web Text)

Max Activating Token Index: 982

Text #5

Max Range: 1.4516. Min Range: -1.4516

Max Act: 1.4513. Min Act: -0.1050

Data Index: 3367659 (Open Web Text)

Max Activating Token Index: 329

Text #6

Max Range: 1.4516. Min Range: -1.4516

Max Act: 1.4325. Min Act: -0.0301

Data Index: 5766488 (Open Web Text)

Max Activating Token Index: 1009

Text #7

Max Range: 1.4516. Min Range: -1.4516

Max Act: 1.4341. Min Act: -0.1514

Data Index: 2447630 (Open Web Text)

Max Activating Token Index: 133

Text #8

Max Range: 1.4516. Min Range: -1.4516

Max Act: 1.4354. Min Act: -0.0768

Data Index: 5482959 (Open Web Text)

Max Activating Token Index: 185

Text #9

Max Range: 1.4516. Min Range: -1.4516

Max Act: 1.4332. Min Act: -0.0906

Data Index: 7927579 (Open Web Text)

Max Activating Token Index: 180

Text #10

Max Range: 1.4516. Min Range: -1.4516

Max Act: 1.4245. Min Act: -0.1481

Data Index: 4624158 (Open Web Text)

Max Activating Token Index: 1015

Text #11

Max Range: 1.4516. Min Range: -1.4516

Max Act: 1.4356. Min Act: -0.1510

Data Index: 2997988 (Open Web Text)

Max Activating Token Index: 711

Text #12

Max Range: 1.4516. Min Range: -1.4516

Max Act: 1.4379. Min Act: -0.0464

Data Index: 3565682 (Open Web Text)

Max Activating Token Index: 174

Text #13

Max Range: 1.4516. Min Range: -1.4516

Max Act: 1.4371. Min Act: -0.0690

Data Index: 6362626 (Open Web Text)

Max Activating Token Index: 155

Text #14

Max Range: 1.4516. Min Range: -1.4516

Max Act: 1.4313. Min Act: -0.0901

Data Index: 2549982 (Open Web Text)

Max Activating Token Index: 45

Text #15

Max Range: 1.4516. Min Range: -1.4516

Max Act: 1.4265. Min Act: -0.0626

Data Index: 1325100 (Open Web Text)

Max Activating Token Index: 1011

Text #16

Max Range: 1.4516. Min Range: -1.4516

Max Act: 1.4287. Min Act: -0.1045

Data Index: 2039593 (Open Web Text)

Max Activating Token Index: 175

Text #17

Max Range: 1.4516. Min Range: -1.4516

Max Act: 1.4322. Min Act: -0.1470

Data Index: 1201436 (Open Web Text)

Max Activating Token Index: 994

Text #18

Max Range: 1.4516. Min Range: -1.4516

Max Act: 1.4247. Min Act: -0.0829

Data Index: 7055583 (Open Web Text)

Max Activating Token Index: 706

Text #19

Max Range: 1.4516. Min Range: -1.4516

Max Act: 1.4213. Min Act: -0.1254

Data Index: 7944643 (Open Web Text)

Max Activating Token Index: 164