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

Dataset: Open Web Text

Neuron 2500 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: 3.1959. Min Range: -3.1959

Max Act: 3.1959. Min Act: -0.1700

Data Index: 1699612 (Open Web Text)

Max Activating Token Index: 590

Text #1

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.1571. Min Act: -0.1700

Data Index: 5446398 (Open Web Text)

Max Activating Token Index: 767

Text #2

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.1421. Min Act: -0.1700

Data Index: 3000695 (Open Web Text)

Max Activating Token Index: 294

Text #3

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.1252. Min Act: -0.1700

Data Index: 7373235 (Open Web Text)

Max Activating Token Index: 649

Text #4

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0883. Min Act: -0.1700

Data Index: 2123313 (Open Web Text)

Max Activating Token Index: 696

Text #5

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0983. Min Act: -0.1700

Data Index: 1929302 (Open Web Text)

Max Activating Token Index: 664

Text #6

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0837. Min Act: -0.1700

Data Index: 4818750 (Open Web Text)

Max Activating Token Index: 540

Text #7

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0875. Min Act: -0.1700

Data Index: 3779747 (Open Web Text)

Max Activating Token Index: 482

Text #8

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0722. Min Act: -0.1700

Data Index: 1168180 (Open Web Text)

Max Activating Token Index: 495

Text #9

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0620. Min Act: -0.1700

Data Index: 8171104 (Open Web Text)

Max Activating Token Index: 524

Text #10

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0612. Min Act: -0.1700

Data Index: 3479118 (Open Web Text)

Max Activating Token Index: 169

Text #11

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0193. Min Act: -0.1700

Data Index: 2917193 (Open Web Text)

Max Activating Token Index: 1011

Text #12

Max Range: 3.1959. Min Range: -3.1959

Max Act: 2.9612. Min Act: -0.1700

Data Index: 8401517 (Open Web Text)

Max Activating Token Index: 439

Text #13

Max Range: 3.1959. Min Range: -3.1959

Max Act: 2.9931. Min Act: -0.1700

Data Index: 1303957 (Open Web Text)

Max Activating Token Index: 297

Text #14

Max Range: 3.1959. Min Range: -3.1959

Max Act: 2.9414. Min Act: -0.1700

Data Index: 4246102 (Open Web Text)

Max Activating Token Index: 858

Text #15

Max Range: 3.1959. Min Range: -3.1959

Max Act: 2.9262. Min Act: -0.1700

Data Index: 1048627 (Open Web Text)

Max Activating Token Index: 559

Text #16

Max Range: 3.1959. Min Range: -3.1959

Max Act: 2.9428. Min Act: -0.1700

Data Index: 599912 (Open Web Text)

Max Activating Token Index: 417

Text #17

Max Range: 3.1959. Min Range: -3.1959

Max Act: 2.9396. Min Act: -0.1700

Data Index: 8221617 (Open Web Text)

Max Activating Token Index: 693

Text #18

Max Range: 3.1959. Min Range: -3.1959

Max Act: 2.9468. Min Act: -0.1700

Data Index: 7104204 (Open Web Text)

Max Activating Token Index: 673

Text #19

Max Range: 3.1959. Min Range: -3.1959

Max Act: 2.9149. Min Act: -0.1700

Data Index: 7648954 (Open Web Text)

Max Activating Token Index: 142