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

Dataset: Open Web Text

Neuron 1206 in Layer 1

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: 4.9536. Min Range: -4.9536

Max Act: 4.9536. Min Act: -0.1700

Data Index: 3287445 (Open Web Text)

Max Activating Token Index: 90

Text #1

Max Range: 4.9536. Min Range: -4.9536

Max Act: 4.9351. Min Act: -0.1700

Data Index: 4897533 (Open Web Text)

Max Activating Token Index: 170

Text #2

Max Range: 4.9536. Min Range: -4.9536

Max Act: 4.9283. Min Act: -0.1700

Data Index: 4157598 (Open Web Text)

Max Activating Token Index: 763

Text #3

Max Range: 4.9536. Min Range: -4.9536

Max Act: 4.8969. Min Act: -0.1700

Data Index: 1713718 (Open Web Text)

Max Activating Token Index: 1019

Text #4

Max Range: 4.9536. Min Range: -4.9536

Max Act: 4.8808. Min Act: -0.1700

Data Index: 3600851 (Open Web Text)

Max Activating Token Index: 165

Text #5

Max Range: 4.9536. Min Range: -4.9536

Max Act: 4.8856. Min Act: -0.1700

Data Index: 6004390 (Open Web Text)

Max Activating Token Index: 61

Text #6

Max Range: 4.9536. Min Range: -4.9536

Max Act: 4.8688. Min Act: -0.1700

Data Index: 6794081 (Open Web Text)

Max Activating Token Index: 510

Text #7

Max Range: 4.9536. Min Range: -4.9536

Max Act: 4.8483. Min Act: -0.1700

Data Index: 7818776 (Open Web Text)

Max Activating Token Index: 681

Text #8

Max Range: 4.9536. Min Range: -4.9536

Max Act: 4.8667. Min Act: -0.1700

Data Index: 8645 (Open Web Text)

Max Activating Token Index: 467

Text #9

Max Range: 4.9536. Min Range: -4.9536

Max Act: 4.8316. Min Act: -0.1700

Data Index: 3052075 (Open Web Text)

Max Activating Token Index: 454

Text #10

Max Range: 4.9536. Min Range: -4.9536

Max Act: 4.8322. Min Act: -0.1700

Data Index: 844147 (Open Web Text)

Max Activating Token Index: 438

Text #11

Max Range: 4.9536. Min Range: -4.9536

Max Act: 4.8444. Min Act: -0.1700

Data Index: 4138670 (Open Web Text)

Max Activating Token Index: 85

Text #12

Max Range: 4.9536. Min Range: -4.9536

Max Act: 4.8250. Min Act: -0.1700

Data Index: 326546 (Open Web Text)

Max Activating Token Index: 808

Text #13

Max Range: 4.9536. Min Range: -4.9536

Max Act: 4.8269. Min Act: -0.1700

Data Index: 7428940 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.9536. Min Range: -4.9536

Max Act: 4.8272. Min Act: -0.1700

Data Index: 4390873 (Open Web Text)

Max Activating Token Index: 546

Text #15

Max Range: 4.9536. Min Range: -4.9536

Max Act: 4.8469. Min Act: -0.1700

Data Index: 4593558 (Open Web Text)

Max Activating Token Index: 704

Text #16

Max Range: 4.9536. Min Range: -4.9536

Max Act: 4.8400. Min Act: -0.1700

Data Index: 8023612 (Open Web Text)

Max Activating Token Index: 614

Text #17

Max Range: 4.9536. Min Range: -4.9536

Max Act: 4.7928. Min Act: -0.1700

Data Index: 1631827 (Open Web Text)

Max Activating Token Index: 406

Text #18

Max Range: 4.9536. Min Range: -4.9536

Max Act: 4.8241. Min Act: -0.1700

Data Index: 5198739 (Open Web Text)

Max Activating Token Index: 508

Text #19

Max Range: 4.9536. Min Range: -4.9536

Max Act: 4.8006. Min Act: -0.1700

Data Index: 5958165 (Open Web Text)

Max Activating Token Index: 182