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

Dataset: Open Web Text

Neuron 1724 in Layer 4

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: 4.3874. Min Range: -4.3874

Max Act: 4.3874. Min Act: -0.1700

Data Index: 7619232 (Open Web Text)

Max Activating Token Index: 598

Text #1

Max Range: 4.3874. Min Range: -4.3874

Max Act: 4.3216. Min Act: -0.1700

Data Index: 164244 (Open Web Text)

Max Activating Token Index: 329

Text #2

Max Range: 4.3874. Min Range: -4.3874

Max Act: 4.2772. Min Act: -0.1700

Data Index: 7465773 (Open Web Text)

Max Activating Token Index: 576

Text #3

Max Range: 4.3874. Min Range: -4.3874

Max Act: 4.2618. Min Act: -0.1700

Data Index: 6621926 (Open Web Text)

Max Activating Token Index: 933

Text #4

Max Range: 4.3874. Min Range: -4.3874

Max Act: 4.1809. Min Act: -0.1700

Data Index: 3449770 (Open Web Text)

Max Activating Token Index: 534

Text #5

Max Range: 4.3874. Min Range: -4.3874

Max Act: 4.1604. Min Act: -0.1700

Data Index: 5002339 (Open Web Text)

Max Activating Token Index: 493

Text #6

Max Range: 4.3874. Min Range: -4.3874

Max Act: 4.1375. Min Act: -0.1700

Data Index: 7190207 (Open Web Text)

Max Activating Token Index: 186

Text #7

Max Range: 4.3874. Min Range: -4.3874

Max Act: 4.1380. Min Act: -0.1700

Data Index: 1807164 (Open Web Text)

Max Activating Token Index: 75

Text #8

Max Range: 4.3874. Min Range: -4.3874

Max Act: 4.0849. Min Act: -0.1700

Data Index: 6338087 (Open Web Text)

Max Activating Token Index: 438

Text #9

Max Range: 4.3874. Min Range: -4.3874

Max Act: 4.1120. Min Act: -0.1700

Data Index: 7039517 (Open Web Text)

Max Activating Token Index: 256

Text #10

Max Range: 4.3874. Min Range: -4.3874

Max Act: 4.0925. Min Act: -0.1700

Data Index: 164243 (Open Web Text)

Max Activating Token Index: 121

Text #11

Max Range: 4.3874. Min Range: -4.3874

Max Act: 4.0799. Min Act: -0.1700

Data Index: 4826761 (Open Web Text)

Max Activating Token Index: 312

Text #12

Max Range: 4.3874. Min Range: -4.3874

Max Act: 4.0970. Min Act: -0.1700

Data Index: 2553290 (Open Web Text)

Max Activating Token Index: 289

Text #13

Max Range: 4.3874. Min Range: -4.3874

Max Act: 4.1398. Min Act: -0.1700

Data Index: 5158985 (Open Web Text)

Max Activating Token Index: 814

Text #14

Max Range: 4.3874. Min Range: -4.3874

Max Act: 4.0570. Min Act: -0.1700

Data Index: 4373060 (Open Web Text)

Max Activating Token Index: 528

Text #15

Max Range: 4.3874. Min Range: -4.3874

Max Act: 4.0574. Min Act: -0.1700

Data Index: 227335 (Open Web Text)

Max Activating Token Index: 665

Text #16

Max Range: 4.3874. Min Range: -4.3874

Max Act: 4.0699. Min Act: -0.1700

Data Index: 6080593 (Open Web Text)

Max Activating Token Index: 356

Text #17

Max Range: 4.3874. Min Range: -4.3874

Max Act: 4.0492. Min Act: -0.1700

Data Index: 188601 (Open Web Text)

Max Activating Token Index: 247

Text #18

Max Range: 4.3874. Min Range: -4.3874

Max Act: 4.0472. Min Act: -0.1700

Data Index: 4897329 (Open Web Text)

Max Activating Token Index: 206

Text #19

Max Range: 4.3874. Min Range: -4.3874

Max Act: 4.0541. Min Act: -0.1700

Data Index: 4957485 (Open Web Text)

Max Activating Token Index: 194