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

Dataset: Open Web Text

Neuron 699 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: 3.0148. Min Range: -3.0148

Max Act: 3.0148. Min Act: -0.1700

Data Index: 981687 (Open Web Text)

Max Activating Token Index: 970

Text #1

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.9740. Min Act: -0.1700

Data Index: 2877951 (Open Web Text)

Max Activating Token Index: 520

Text #2

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.9479. Min Act: -0.1700

Data Index: 7940258 (Open Web Text)

Max Activating Token Index: 291

Text #3

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.9505. Min Act: -0.1700

Data Index: 7384546 (Open Web Text)

Max Activating Token Index: 532

Text #4

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.9311. Min Act: -0.1700

Data Index: 4889970 (Open Web Text)

Max Activating Token Index: 350

Text #5

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.9231. Min Act: -0.1700

Data Index: 3549566 (Open Web Text)

Max Activating Token Index: 1015

Text #6

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.9198. Min Act: -0.1700

Data Index: 1534990 (Open Web Text)

Max Activating Token Index: 594

Text #7

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.9016. Min Act: -0.1700

Data Index: 399254 (Open Web Text)

Max Activating Token Index: 359

Text #8

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.9055. Min Act: -0.1700

Data Index: 6066908 (Open Web Text)

Max Activating Token Index: 162

Text #9

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.9145. Min Act: -0.1700

Data Index: 2916111 (Open Web Text)

Max Activating Token Index: 778

Text #10

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8516. Min Act: -0.1700

Data Index: 2757023 (Open Web Text)

Max Activating Token Index: 176

Text #11

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8733. Min Act: -0.1700

Data Index: 7892589 (Open Web Text)

Max Activating Token Index: 61

Text #12

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8490. Min Act: -0.1700

Data Index: 1197545 (Open Web Text)

Max Activating Token Index: 348

Text #13

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8837. Min Act: -0.1700

Data Index: 2125562 (Open Web Text)

Max Activating Token Index: 490

Text #14

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8408. Min Act: -0.1700

Data Index: 5598493 (Open Web Text)

Max Activating Token Index: 372

Text #15

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8470. Min Act: -0.1700

Data Index: 5513731 (Open Web Text)

Max Activating Token Index: 301

Text #16

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.9123. Min Act: -0.1700

Data Index: 7624093 (Open Web Text)

Max Activating Token Index: 763

Text #17

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8408. Min Act: -0.1700

Data Index: 7387215 (Open Web Text)

Max Activating Token Index: 448

Text #18

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8625. Min Act: -0.1700

Data Index: 7895341 (Open Web Text)

Max Activating Token Index: 261

Text #19

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8372. Min Act: -0.1700

Data Index: 2639906 (Open Web Text)

Max Activating Token Index: 243