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

Dataset: Open Web Text

Neuron 679 in Layer 6

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: 4.4045. Min Range: -4.4045

Max Act: 4.4045. Min Act: -0.1700

Data Index: 8161589 (Open Web Text)

Max Activating Token Index: 170

Text #1

Max Range: 4.4045. Min Range: -4.4045

Max Act: 4.3893. Min Act: -0.1700

Data Index: 8188695 (Open Web Text)

Max Activating Token Index: 675

Text #2

Max Range: 4.4045. Min Range: -4.4045

Max Act: 4.3760. Min Act: -0.1700

Data Index: 7878834 (Open Web Text)

Max Activating Token Index: 684

Text #3

Max Range: 4.4045. Min Range: -4.4045

Max Act: 4.3028. Min Act: -0.1700

Data Index: 4073813 (Open Web Text)

Max Activating Token Index: 138

Text #4

Max Range: 4.4045. Min Range: -4.4045

Max Act: 4.2929. Min Act: -0.1700

Data Index: 1582587 (Open Web Text)

Max Activating Token Index: 182

Text #5

Max Range: 4.4045. Min Range: -4.4045

Max Act: 4.2949. Min Act: -0.1700

Data Index: 7485837 (Open Web Text)

Max Activating Token Index: 142

Text #6

Max Range: 4.4045. Min Range: -4.4045

Max Act: 4.2757. Min Act: -0.1700

Data Index: 1944886 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 4.4045. Min Range: -4.4045

Max Act: 4.2521. Min Act: -0.1700

Data Index: 1257469 (Open Web Text)

Max Activating Token Index: 633

Text #8

Max Range: 4.4045. Min Range: -4.4045

Max Act: 4.2721. Min Act: -0.1700

Data Index: 2401628 (Open Web Text)

Max Activating Token Index: 253

Text #9

Max Range: 4.4045. Min Range: -4.4045

Max Act: 4.2494. Min Act: -0.1700

Data Index: 2892994 (Open Web Text)

Max Activating Token Index: 116

Text #10

Max Range: 4.4045. Min Range: -4.4045

Max Act: 4.2491. Min Act: -0.1700

Data Index: 2122 (Open Web Text)

Max Activating Token Index: 679

Text #11

Max Range: 4.4045. Min Range: -4.4045

Max Act: 4.2364. Min Act: -0.1700

Data Index: 4447602 (Open Web Text)

Max Activating Token Index: 839

Text #12

Max Range: 4.4045. Min Range: -4.4045

Max Act: 4.1825. Min Act: -0.1700

Data Index: 5764334 (Open Web Text)

Max Activating Token Index: 296

Text #13

Max Range: 4.4045. Min Range: -4.4045

Max Act: 4.2048. Min Act: -0.1700

Data Index: 5293966 (Open Web Text)

Max Activating Token Index: 394

Text #14

Max Range: 4.4045. Min Range: -4.4045

Max Act: 4.1840. Min Act: -0.1700

Data Index: 4120495 (Open Web Text)

Max Activating Token Index: 756

Text #15

Max Range: 4.4045. Min Range: -4.4045

Max Act: 4.1168. Min Act: -0.1700

Data Index: 6239661 (Open Web Text)

Max Activating Token Index: 760

Text #16

Max Range: 4.4045. Min Range: -4.4045

Max Act: 4.1658. Min Act: -0.1700

Data Index: 7169089 (Open Web Text)

Max Activating Token Index: 669

Text #17

Max Range: 4.4045. Min Range: -4.4045

Max Act: 4.2045. Min Act: -0.1700

Data Index: 7569851 (Open Web Text)

Max Activating Token Index: 715

Text #18

Max Range: 4.4045. Min Range: -4.4045

Max Act: 4.1215. Min Act: -0.1700

Data Index: 3562803 (Open Web Text)

Max Activating Token Index: 574

Text #19

Max Range: 4.4045. Min Range: -4.4045

Max Act: 4.1709. Min Act: -0.1700

Data Index: 4846502 (Open Web Text)

Max Activating Token Index: 453