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

Dataset: Open Web Text

Neuron 884 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: 4.2406. Min Range: -4.2406

Max Act: 4.2406. Min Act: -0.1700

Data Index: 138130 (Open Web Text)

Max Activating Token Index: 747

Text #1

Max Range: 4.2406. Min Range: -4.2406

Max Act: 4.1435. Min Act: -0.1700

Data Index: 6168715 (Open Web Text)

Max Activating Token Index: 111

Text #2

Max Range: 4.2406. Min Range: -4.2406

Max Act: 4.1367. Min Act: -0.1700

Data Index: 6794991 (Open Web Text)

Max Activating Token Index: 808

Text #3

Max Range: 4.2406. Min Range: -4.2406

Max Act: 4.0894. Min Act: -0.1700

Data Index: 3135123 (Open Web Text)

Max Activating Token Index: 470

Text #4

Max Range: 4.2406. Min Range: -4.2406

Max Act: 4.0808. Min Act: -0.1700

Data Index: 4612879 (Open Web Text)

Max Activating Token Index: 335

Text #5

Max Range: 4.2406. Min Range: -4.2406

Max Act: 4.0697. Min Act: -0.1700

Data Index: 1008167 (Open Web Text)

Max Activating Token Index: 1000

Text #6

Max Range: 4.2406. Min Range: -4.2406

Max Act: 4.0843. Min Act: -0.1700

Data Index: 8152519 (Open Web Text)

Max Activating Token Index: 827

Text #7

Max Range: 4.2406. Min Range: -4.2406

Max Act: 4.0882. Min Act: -0.1700

Data Index: 912161 (Open Web Text)

Max Activating Token Index: 748

Text #8

Max Range: 4.2406. Min Range: -4.2406

Max Act: 4.0345. Min Act: -0.1700

Data Index: 2831731 (Open Web Text)

Max Activating Token Index: 370

Text #9

Max Range: 4.2406. Min Range: -4.2406

Max Act: 3.9988. Min Act: -0.1700

Data Index: 3253977 (Open Web Text)

Max Activating Token Index: 84

Text #10

Max Range: 4.2406. Min Range: -4.2406

Max Act: 3.9514. Min Act: -0.1700

Data Index: 7016274 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 4.2406. Min Range: -4.2406

Max Act: 3.9671. Min Act: -0.1700

Data Index: 1617058 (Open Web Text)

Max Activating Token Index: 191

Text #12

Max Range: 4.2406. Min Range: -4.2406

Max Act: 3.9335. Min Act: -0.1700

Data Index: 6032956 (Open Web Text)

Max Activating Token Index: 1022

Text #13

Max Range: 4.2406. Min Range: -4.2406

Max Act: 3.9522. Min Act: -0.1700

Data Index: 748225 (Open Web Text)

Max Activating Token Index: 427

Text #14

Max Range: 4.2406. Min Range: -4.2406

Max Act: 3.9082. Min Act: -0.1700

Data Index: 3540724 (Open Web Text)

Max Activating Token Index: 726

Text #15

Max Range: 4.2406. Min Range: -4.2406

Max Act: 3.9551. Min Act: -0.1700

Data Index: 6448701 (Open Web Text)

Max Activating Token Index: 910

Text #16

Max Range: 4.2406. Min Range: -4.2406

Max Act: 3.9258. Min Act: -0.1700

Data Index: 6227211 (Open Web Text)

Max Activating Token Index: 247

Text #17

Max Range: 4.2406. Min Range: -4.2406

Max Act: 3.9513. Min Act: -0.1700

Data Index: 5562297 (Open Web Text)

Max Activating Token Index: 565

Text #18

Max Range: 4.2406. Min Range: -4.2406

Max Act: 3.9305. Min Act: -0.1700

Data Index: 2164753 (Open Web Text)

Max Activating Token Index: 317

Text #19

Max Range: 4.2406. Min Range: -4.2406

Max Act: 3.9022. Min Act: -0.1700

Data Index: 4162776 (Open Web Text)

Max Activating Token Index: 243