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

Dataset: Open Web Text

Neuron 258 in Layer 6

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: 3.4364. Min Range: -3.4364

Max Act: 3.4364. Min Act: -0.1700

Data Index: 3372484 (Open Web Text)

Max Activating Token Index: 666

Text #1

Max Range: 3.4364. Min Range: -3.4364

Max Act: 3.4123. Min Act: -0.1700

Data Index: 4086156 (Open Web Text)

Max Activating Token Index: 837

Text #2

Max Range: 3.4364. Min Range: -3.4364

Max Act: 3.2566. Min Act: -0.1700

Data Index: 2080505 (Open Web Text)

Max Activating Token Index: 672

Text #3

Max Range: 3.4364. Min Range: -3.4364

Max Act: 3.2294. Min Act: -0.1700

Data Index: 2527579 (Open Web Text)

Max Activating Token Index: 837

Text #4

Max Range: 3.4364. Min Range: -3.4364

Max Act: 3.2369. Min Act: -0.1700

Data Index: 3350871 (Open Web Text)

Max Activating Token Index: 324

Text #5

Max Range: 3.4364. Min Range: -3.4364

Max Act: 3.1717. Min Act: -0.1700

Data Index: 8759809 (Open Web Text)

Max Activating Token Index: 592

Text #6

Max Range: 3.4364. Min Range: -3.4364

Max Act: 3.1624. Min Act: -0.1700

Data Index: 8544229 (Open Web Text)

Max Activating Token Index: 180

Text #7

Max Range: 3.4364. Min Range: -3.4364

Max Act: 3.1782. Min Act: -0.1700

Data Index: 6810003 (Open Web Text)

Max Activating Token Index: 218

Text #8

Max Range: 3.4364. Min Range: -3.4364

Max Act: 3.1485. Min Act: -0.1700

Data Index: 5728776 (Open Web Text)

Max Activating Token Index: 215

Text #9

Max Range: 3.4364. Min Range: -3.4364

Max Act: 3.1384. Min Act: -0.1700

Data Index: 3670368 (Open Web Text)

Max Activating Token Index: 504

Text #10

Max Range: 3.4364. Min Range: -3.4364

Max Act: 3.1224. Min Act: -0.1700

Data Index: 2425194 (Open Web Text)

Max Activating Token Index: 612

Text #11

Max Range: 3.4364. Min Range: -3.4364

Max Act: 3.1408. Min Act: -0.1700

Data Index: 2828803 (Open Web Text)

Max Activating Token Index: 352

Text #12

Max Range: 3.4364. Min Range: -3.4364

Max Act: 3.1363. Min Act: -0.1700

Data Index: 8796500 (Open Web Text)

Max Activating Token Index: 63

Text #13

Max Range: 3.4364. Min Range: -3.4364

Max Act: 3.1259. Min Act: -0.1700

Data Index: 8367151 (Open Web Text)

Max Activating Token Index: 604

Text #14

Max Range: 3.4364. Min Range: -3.4364

Max Act: 3.1084. Min Act: -0.1700

Data Index: 886860 (Open Web Text)

Max Activating Token Index: 382

Text #15

Max Range: 3.4364. Min Range: -3.4364

Max Act: 3.1102. Min Act: -0.1700

Data Index: 6758457 (Open Web Text)

Max Activating Token Index: 166

Text #16

Max Range: 3.4364. Min Range: -3.4364

Max Act: 3.0960. Min Act: -0.1700

Data Index: 5178133 (Open Web Text)

Max Activating Token Index: 108

Text #17

Max Range: 3.4364. Min Range: -3.4364

Max Act: 3.1033. Min Act: -0.1700

Data Index: 8366156 (Open Web Text)

Max Activating Token Index: 763

Text #18

Max Range: 3.4364. Min Range: -3.4364

Max Act: 3.0800. Min Act: -0.1700

Data Index: 588195 (Open Web Text)

Max Activating Token Index: 859

Text #19

Max Range: 3.4364. Min Range: -3.4364

Max Act: 3.1024. Min Act: -0.1700

Data Index: 1636859 (Open Web Text)

Max Activating Token Index: 530