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

Dataset: Open Web Text

Neuron 1188 in Layer 5

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: 3.4490. Min Range: -3.4490

Max Act: 3.4396. Min Act: -0.1700

Data Index: 80995 (Open Web Text)

Max Activating Token Index: 552

Text #1

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.4316. Min Act: -0.1700

Data Index: 4725496 (Open Web Text)

Max Activating Token Index: 426

Text #2

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.4490. Min Act: -0.1700

Data Index: 2606176 (Open Web Text)

Max Activating Token Index: 104

Text #3

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.3791. Min Act: -0.1700

Data Index: 1865241 (Open Web Text)

Max Activating Token Index: 669

Text #4

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.3927. Min Act: -0.1700

Data Index: 8748174 (Open Web Text)

Max Activating Token Index: 494

Text #5

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.4099. Min Act: -0.1700

Data Index: 8119365 (Open Web Text)

Max Activating Token Index: 777

Text #6

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.3802. Min Act: -0.1700

Data Index: 5471786 (Open Web Text)

Max Activating Token Index: 220

Text #7

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.3353. Min Act: -0.1700

Data Index: 666256 (Open Web Text)

Max Activating Token Index: 64

Text #8

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.3520. Min Act: -0.1700

Data Index: 8418999 (Open Web Text)

Max Activating Token Index: 723

Text #9

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.3102. Min Act: -0.1700

Data Index: 1933453 (Open Web Text)

Max Activating Token Index: 812

Text #10

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.3574. Min Act: -0.1700

Data Index: 6892941 (Open Web Text)

Max Activating Token Index: 339

Text #11

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.2710. Min Act: -0.1700

Data Index: 884304 (Open Web Text)

Max Activating Token Index: 942

Text #12

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.3374. Min Act: -0.1700

Data Index: 1357321 (Open Web Text)

Max Activating Token Index: 567

Text #13

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.3436. Min Act: -0.1700

Data Index: 3171277 (Open Web Text)

Max Activating Token Index: 451

Text #14

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.3568. Min Act: -0.1700

Data Index: 672392 (Open Web Text)

Max Activating Token Index: 121

Text #15

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.3524. Min Act: -0.1700

Data Index: 6317590 (Open Web Text)

Max Activating Token Index: 820

Text #16

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.3038. Min Act: -0.1700

Data Index: 2443062 (Open Web Text)

Max Activating Token Index: 448

Text #17

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.3271. Min Act: -0.1700

Data Index: 4012535 (Open Web Text)

Max Activating Token Index: 327

Text #18

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.3332. Min Act: -0.1700

Data Index: 4291495 (Open Web Text)

Max Activating Token Index: 660

Text #19

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.3194. Min Act: -0.1700

Data Index: 6546330 (Open Web Text)

Max Activating Token Index: 56