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

Dataset: Open Web Text

Neuron 3055 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: 3.6488. Min Range: -3.6488

Max Act: 3.6488. Min Act: -0.1700

Data Index: 7029380 (Open Web Text)

Max Activating Token Index: 604

Text #1

Max Range: 3.6488. Min Range: -3.6488

Max Act: 3.6192. Min Act: -0.1700

Data Index: 8442348 (Open Web Text)

Max Activating Token Index: 653

Text #2

Max Range: 3.6488. Min Range: -3.6488

Max Act: 3.5746. Min Act: -0.1700

Data Index: 5940630 (Open Web Text)

Max Activating Token Index: 513

Text #3

Max Range: 3.6488. Min Range: -3.6488

Max Act: 3.5393. Min Act: -0.1700

Data Index: 929976 (Open Web Text)

Max Activating Token Index: 384

Text #4

Max Range: 3.6488. Min Range: -3.6488

Max Act: 3.5256. Min Act: -0.1700

Data Index: 6585871 (Open Web Text)

Max Activating Token Index: 908

Text #5

Max Range: 3.6488. Min Range: -3.6488

Max Act: 3.5454. Min Act: -0.1700

Data Index: 6111816 (Open Web Text)

Max Activating Token Index: 998

Text #6

Max Range: 3.6488. Min Range: -3.6488

Max Act: 3.5209. Min Act: -0.1700

Data Index: 6038291 (Open Web Text)

Max Activating Token Index: 454

Text #7

Max Range: 3.6488. Min Range: -3.6488

Max Act: 3.5207. Min Act: -0.1700

Data Index: 2102955 (Open Web Text)

Max Activating Token Index: 665

Text #8

Max Range: 3.6488. Min Range: -3.6488

Max Act: 3.4931. Min Act: -0.1700

Data Index: 4784607 (Open Web Text)

Max Activating Token Index: 69

Text #9

Max Range: 3.6488. Min Range: -3.6488

Max Act: 3.4872. Min Act: -0.1700

Data Index: 7135924 (Open Web Text)

Max Activating Token Index: 145

Text #10

Max Range: 3.6488. Min Range: -3.6488

Max Act: 3.4897. Min Act: -0.1700

Data Index: 7591210 (Open Web Text)

Max Activating Token Index: 200

Text #11

Max Range: 3.6488. Min Range: -3.6488

Max Act: 3.5006. Min Act: -0.1700

Data Index: 899129 (Open Web Text)

Max Activating Token Index: 668

Text #12

Max Range: 3.6488. Min Range: -3.6488

Max Act: 3.4863. Min Act: -0.1700

Data Index: 739786 (Open Web Text)

Max Activating Token Index: 306

Text #13

Max Range: 3.6488. Min Range: -3.6488

Max Act: 3.4530. Min Act: -0.1700

Data Index: 7930754 (Open Web Text)

Max Activating Token Index: 573

Text #14

Max Range: 3.6488. Min Range: -3.6488

Max Act: 3.4593. Min Act: -0.1700

Data Index: 7714208 (Open Web Text)

Max Activating Token Index: 516

Text #15

Max Range: 3.6488. Min Range: -3.6488

Max Act: 3.4472. Min Act: -0.1700

Data Index: 4048258 (Open Web Text)

Max Activating Token Index: 226

Text #16

Max Range: 3.6488. Min Range: -3.6488

Max Act: 3.4699. Min Act: -0.1700

Data Index: 986425 (Open Web Text)

Max Activating Token Index: 479

Text #17

Max Range: 3.6488. Min Range: -3.6488

Max Act: 3.4708. Min Act: -0.1700

Data Index: 4939101 (Open Web Text)

Max Activating Token Index: 917

Text #18

Max Range: 3.6488. Min Range: -3.6488

Max Act: 3.4387. Min Act: -0.1700

Data Index: 1153788 (Open Web Text)

Max Activating Token Index: 363

Text #19

Max Range: 3.6488. Min Range: -3.6488

Max Act: 3.4443. Min Act: -0.1700

Data Index: 636978 (Open Web Text)

Max Activating Token Index: 442