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

Dataset: Open Web Text

Neuron 1516 in Layer 2

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: 2.3613. Min Range: -2.3613

Max Act: 2.3613. Min Act: -0.1700

Data Index: 1891403 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 2.3613. Min Range: -2.3613

Max Act: 2.3330. Min Act: -0.1700

Data Index: 4119693 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.3613. Min Range: -2.3613

Max Act: 2.3228. Min Act: -0.1700

Data Index: 502684 (Open Web Text)

Max Activating Token Index: 170

Text #3

Max Range: 2.3613. Min Range: -2.3613

Max Act: 2.3115. Min Act: -0.1700

Data Index: 6107783 (Open Web Text)

Max Activating Token Index: 580

Text #4

Max Range: 2.3613. Min Range: -2.3613

Max Act: 2.3242. Min Act: -0.1700

Data Index: 6651708 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.3613. Min Range: -2.3613

Max Act: 2.3222. Min Act: -0.1700

Data Index: 502683 (Open Web Text)

Max Activating Token Index: 437

Text #6

Max Range: 2.3613. Min Range: -2.3613

Max Act: 2.2942. Min Act: -0.1700

Data Index: 4016163 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 2.3613. Min Range: -2.3613

Max Act: 2.2831. Min Act: -0.1700

Data Index: 2662766 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 2.3613. Min Range: -2.3613

Max Act: 2.2637. Min Act: -0.1700

Data Index: 8321542 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 2.3613. Min Range: -2.3613

Max Act: 2.2527. Min Act: -0.1700

Data Index: 6699508 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.3613. Min Range: -2.3613

Max Act: 2.2702. Min Act: -0.1700

Data Index: 3045050 (Open Web Text)

Max Activating Token Index: 14

Text #11

Max Range: 2.3613. Min Range: -2.3613

Max Act: 2.2302. Min Act: -0.1700

Data Index: 5155059 (Open Web Text)

Max Activating Token Index: 884

Text #12

Max Range: 2.3613. Min Range: -2.3613

Max Act: 2.2598. Min Act: -0.1700

Data Index: 5719104 (Open Web Text)

Max Activating Token Index: 683

Text #13

Max Range: 2.3613. Min Range: -2.3613

Max Act: 2.2355. Min Act: -0.1700

Data Index: 1760496 (Open Web Text)

Max Activating Token Index: 270

Text #14

Max Range: 2.3613. Min Range: -2.3613

Max Act: 2.2312. Min Act: -0.1700

Data Index: 3230927 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 2.3613. Min Range: -2.3613

Max Act: 2.2292. Min Act: -0.1700

Data Index: 1675482 (Open Web Text)

Max Activating Token Index: 567

Text #16

Max Range: 2.3613. Min Range: -2.3613

Max Act: 2.2318. Min Act: -0.1700

Data Index: 2798978 (Open Web Text)

Max Activating Token Index: 20

Text #17

Max Range: 2.3613. Min Range: -2.3613

Max Act: 2.2161. Min Act: -0.1700

Data Index: 8175668 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.3613. Min Range: -2.3613

Max Act: 2.1958. Min Act: -0.1700

Data Index: 7990780 (Open Web Text)

Max Activating Token Index: 520

Text #19

Max Range: 2.3613. Min Range: -2.3613

Max Act: 2.1911. Min Act: -0.1700

Data Index: 6074652 (Open Web Text)

Max Activating Token Index: 6