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

Dataset: Open Web Text

Neuron 1998 in Layer 3

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: 4.1346. Min Range: -4.1346

Max Act: 4.1346. Min Act: -0.1700

Data Index: 7382546 (Open Web Text)

Max Activating Token Index: 46

Text #1

Max Range: 4.1346. Min Range: -4.1346

Max Act: 4.1183. Min Act: -0.1700

Data Index: 8071278 (Open Web Text)

Max Activating Token Index: 56

Text #2

Max Range: 4.1346. Min Range: -4.1346

Max Act: 4.1169. Min Act: -0.1700

Data Index: 8534186 (Open Web Text)

Max Activating Token Index: 349

Text #3

Max Range: 4.1346. Min Range: -4.1346

Max Act: 4.0887. Min Act: -0.1700

Data Index: 7434654 (Open Web Text)

Max Activating Token Index: 31

Text #4

Max Range: 4.1346. Min Range: -4.1346

Max Act: 4.0915. Min Act: -0.1700

Data Index: 8649342 (Open Web Text)

Max Activating Token Index: 401

Text #5

Max Range: 4.1346. Min Range: -4.1346

Max Act: 4.0679. Min Act: -0.1700

Data Index: 7720048 (Open Web Text)

Max Activating Token Index: 33

Text #6

Max Range: 4.1346. Min Range: -4.1346

Max Act: 4.0026. Min Act: -0.1700

Data Index: 2670617 (Open Web Text)

Max Activating Token Index: 692

Text #7

Max Range: 4.1346. Min Range: -4.1346

Max Act: 4.1325. Min Act: -0.1700

Data Index: 7765723 (Open Web Text)

Max Activating Token Index: 327

Text #8

Max Range: 4.1346. Min Range: -4.1346

Max Act: 4.1151. Min Act: -0.1700

Data Index: 8434774 (Open Web Text)

Max Activating Token Index: 933

Text #9

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.8729. Min Act: -0.1700

Data Index: 1661338 (Open Web Text)

Max Activating Token Index: 658

Text #10

Max Range: 4.1346. Min Range: -4.1346

Max Act: 4.0166. Min Act: -0.1700

Data Index: 172708 (Open Web Text)

Max Activating Token Index: 702

Text #11

Max Range: 4.1346. Min Range: -4.1346

Max Act: 4.1049. Min Act: -0.1700

Data Index: 5985400 (Open Web Text)

Max Activating Token Index: 965

Text #12

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.9503. Min Act: -0.1700

Data Index: 1887085 (Open Web Text)

Max Activating Token Index: 420

Text #13

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.9726. Min Act: -0.1700

Data Index: 724458 (Open Web Text)

Max Activating Token Index: 133

Text #14

Max Range: 4.1346. Min Range: -4.1346

Max Act: 4.0029. Min Act: -0.1700

Data Index: 7416038 (Open Web Text)

Max Activating Token Index: 595

Text #15

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.9049. Min Act: -0.1700

Data Index: 5632781 (Open Web Text)

Max Activating Token Index: 488

Text #16

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.9793. Min Act: -0.1700

Data Index: 2436632 (Open Web Text)

Max Activating Token Index: 488

Text #17

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.9671. Min Act: -0.1700

Data Index: 5411735 (Open Web Text)

Max Activating Token Index: 574

Text #18

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.9415. Min Act: -0.1700

Data Index: 3213864 (Open Web Text)

Max Activating Token Index: 330

Text #19

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.9910. Min Act: -0.1700

Data Index: 2564690 (Open Web Text)

Max Activating Token Index: 315