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

Dataset: Open Web Text

Neuron 10 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: 4.3132. Min Range: -4.3132

Max Act: 4.3028. Min Act: -0.1700

Data Index: 5549097 (Open Web Text)

Max Activating Token Index: 999

Text #1

Max Range: 4.3132. Min Range: -4.3132

Max Act: 4.3132. Min Act: -0.1700

Data Index: 7445127 (Open Web Text)

Max Activating Token Index: 469

Text #2

Max Range: 4.3132. Min Range: -4.3132

Max Act: 4.2913. Min Act: -0.1700

Data Index: 2598146 (Open Web Text)

Max Activating Token Index: 92

Text #3

Max Range: 4.3132. Min Range: -4.3132

Max Act: 4.2755. Min Act: -0.1700

Data Index: 6327807 (Open Web Text)

Max Activating Token Index: 940

Text #4

Max Range: 4.3132. Min Range: -4.3132

Max Act: 4.2427. Min Act: -0.1700

Data Index: 5950557 (Open Web Text)

Max Activating Token Index: 300

Text #5

Max Range: 4.3132. Min Range: -4.3132

Max Act: 4.2321. Min Act: -0.1700

Data Index: 7280658 (Open Web Text)

Max Activating Token Index: 125

Text #6

Max Range: 4.3132. Min Range: -4.3132

Max Act: 4.2150. Min Act: -0.1700

Data Index: 3702497 (Open Web Text)

Max Activating Token Index: 129

Text #7

Max Range: 4.3132. Min Range: -4.3132

Max Act: 4.1964. Min Act: -0.1700

Data Index: 522740 (Open Web Text)

Max Activating Token Index: 215

Text #8

Max Range: 4.3132. Min Range: -4.3132

Max Act: 4.2216. Min Act: -0.1700

Data Index: 705541 (Open Web Text)

Max Activating Token Index: 1010

Text #9

Max Range: 4.3132. Min Range: -4.3132

Max Act: 4.1636. Min Act: -0.1700

Data Index: 2197502 (Open Web Text)

Max Activating Token Index: 257

Text #10

Max Range: 4.3132. Min Range: -4.3132

Max Act: 4.1908. Min Act: -0.1700

Data Index: 6389167 (Open Web Text)

Max Activating Token Index: 303

Text #11

Max Range: 4.3132. Min Range: -4.3132

Max Act: 4.1748. Min Act: -0.1700

Data Index: 4859633 (Open Web Text)

Max Activating Token Index: 264

Text #12

Max Range: 4.3132. Min Range: -4.3132

Max Act: 4.1476. Min Act: -0.1700

Data Index: 6306190 (Open Web Text)

Max Activating Token Index: 459

Text #13

Max Range: 4.3132. Min Range: -4.3132

Max Act: 4.1702. Min Act: -0.1700

Data Index: 1967335 (Open Web Text)

Max Activating Token Index: 981

Text #14

Max Range: 4.3132. Min Range: -4.3132

Max Act: 4.1994. Min Act: -0.1700

Data Index: 7792057 (Open Web Text)

Max Activating Token Index: 668

Text #15

Max Range: 4.3132. Min Range: -4.3132

Max Act: 4.1912. Min Act: -0.1700

Data Index: 3088590 (Open Web Text)

Max Activating Token Index: 797

Text #16

Max Range: 4.3132. Min Range: -4.3132

Max Act: 4.1436. Min Act: -0.1700

Data Index: 1904297 (Open Web Text)

Max Activating Token Index: 210

Text #17

Max Range: 4.3132. Min Range: -4.3132

Max Act: 4.1385. Min Act: -0.1700

Data Index: 5554417 (Open Web Text)

Max Activating Token Index: 397

Text #18

Max Range: 4.3132. Min Range: -4.3132

Max Act: 4.1093. Min Act: -0.1700

Data Index: 5757096 (Open Web Text)

Max Activating Token Index: 790

Text #19

Max Range: 4.3132. Min Range: -4.3132

Max Act: 4.1600. Min Act: -0.1700

Data Index: 3036675 (Open Web Text)

Max Activating Token Index: 529