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

Dataset: Open Web Text

Neuron 2809 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: 3.0457. Min Range: -3.0457

Max Act: 3.0457. Min Act: -0.1700

Data Index: 2593224 (Open Web Text)

Max Activating Token Index: 651

Text #1

Max Range: 3.0457. Min Range: -3.0457

Max Act: 3.0150. Min Act: -0.1700

Data Index: 5256715 (Open Web Text)

Max Activating Token Index: 421

Text #2

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.9378. Min Act: -0.1700

Data Index: 3841918 (Open Web Text)

Max Activating Token Index: 108

Text #3

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.9237. Min Act: -0.1700

Data Index: 4435401 (Open Web Text)

Max Activating Token Index: 714

Text #4

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.8999. Min Act: -0.1700

Data Index: 2069978 (Open Web Text)

Max Activating Token Index: 876

Text #5

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.8975. Min Act: -0.1700

Data Index: 1133390 (Open Web Text)

Max Activating Token Index: 739

Text #6

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.8559. Min Act: -0.1700

Data Index: 5606527 (Open Web Text)

Max Activating Token Index: 367

Text #7

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.8376. Min Act: -0.1700

Data Index: 4787574 (Open Web Text)

Max Activating Token Index: 237

Text #8

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.8415. Min Act: -0.1700

Data Index: 4665 (Open Web Text)

Max Activating Token Index: 364

Text #9

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.8336. Min Act: -0.1700

Data Index: 4080651 (Open Web Text)

Max Activating Token Index: 581

Text #10

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.7891. Min Act: -0.1700

Data Index: 5263824 (Open Web Text)

Max Activating Token Index: 433

Text #11

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.8274. Min Act: -0.1700

Data Index: 5261812 (Open Web Text)

Max Activating Token Index: 353

Text #12

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.8031. Min Act: -0.1700

Data Index: 8803610 (Open Web Text)

Max Activating Token Index: 254

Text #13

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.8034. Min Act: -0.1700

Data Index: 6021392 (Open Web Text)

Max Activating Token Index: 180

Text #14

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.8082. Min Act: -0.1700

Data Index: 1470410 (Open Web Text)

Max Activating Token Index: 332

Text #15

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.7594. Min Act: -0.1700

Data Index: 577692 (Open Web Text)

Max Activating Token Index: 386

Text #16

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.7777. Min Act: -0.1700

Data Index: 3090567 (Open Web Text)

Max Activating Token Index: 217

Text #17

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.7544. Min Act: -0.1700

Data Index: 1202646 (Open Web Text)

Max Activating Token Index: 231

Text #18

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.7231. Min Act: -0.1700

Data Index: 4735532 (Open Web Text)

Max Activating Token Index: 115

Text #19

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.7244. Min Act: -0.1700

Data Index: 3678206 (Open Web Text)

Max Activating Token Index: 479