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

Dataset: Open Web Text

Neuron 756 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: 3.3192. Min Range: -3.3192

Max Act: 3.2989. Min Act: -0.1700

Data Index: 4299640 (Open Web Text)

Max Activating Token Index: 962

Text #1

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.3192. Min Act: -0.1700

Data Index: 2927192 (Open Web Text)

Max Activating Token Index: 960

Text #2

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.2944. Min Act: -0.1700

Data Index: 5099963 (Open Web Text)

Max Activating Token Index: 304

Text #3

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.3082. Min Act: -0.1700

Data Index: 8796998 (Open Web Text)

Max Activating Token Index: 1008

Text #4

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.2691. Min Act: -0.1700

Data Index: 1546453 (Open Web Text)

Max Activating Token Index: 595

Text #5

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.2588. Min Act: -0.1700

Data Index: 6578715 (Open Web Text)

Max Activating Token Index: 685

Text #6

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.2725. Min Act: -0.1700

Data Index: 5227031 (Open Web Text)

Max Activating Token Index: 333

Text #7

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.2625. Min Act: -0.1700

Data Index: 7449873 (Open Web Text)

Max Activating Token Index: 533

Text #8

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.2492. Min Act: -0.1700

Data Index: 8369640 (Open Web Text)

Max Activating Token Index: 297

Text #9

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.2188. Min Act: -0.1700

Data Index: 856199 (Open Web Text)

Max Activating Token Index: 798

Text #10

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.2603. Min Act: -0.1700

Data Index: 579337 (Open Web Text)

Max Activating Token Index: 487

Text #11

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.2304. Min Act: -0.1700

Data Index: 2670065 (Open Web Text)

Max Activating Token Index: 220

Text #12

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.2267. Min Act: -0.1700

Data Index: 3804101 (Open Web Text)

Max Activating Token Index: 490

Text #13

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.2440. Min Act: -0.1700

Data Index: 1799224 (Open Web Text)

Max Activating Token Index: 474

Text #14

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.2200. Min Act: -0.1700

Data Index: 1592222 (Open Web Text)

Max Activating Token Index: 707

Text #15

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.2123. Min Act: -0.1700

Data Index: 3686875 (Open Web Text)

Max Activating Token Index: 740

Text #16

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.2429. Min Act: -0.1700

Data Index: 6725488 (Open Web Text)

Max Activating Token Index: 884

Text #17

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.2125. Min Act: -0.1700

Data Index: 4139710 (Open Web Text)

Max Activating Token Index: 983

Text #18

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.2189. Min Act: -0.1700

Data Index: 2374861 (Open Web Text)

Max Activating Token Index: 457

Text #19

Max Range: 3.3192. Min Range: -3.3192

Max Act: 3.2075. Min Act: -0.1700

Data Index: 4139949 (Open Web Text)

Max Activating Token Index: 809