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

Dataset: Open Web Text

Neuron 664 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: 3.2292. Min Range: -3.2292

Max Act: 3.2120. Min Act: -0.1700

Data Index: 2706581 (Open Web Text)

Max Activating Token Index: 719

Text #1

Max Range: 3.2292. Min Range: -3.2292

Max Act: 3.2292. Min Act: -0.1700

Data Index: 1664833 (Open Web Text)

Max Activating Token Index: 572

Text #2

Max Range: 3.2292. Min Range: -3.2292

Max Act: 3.1905. Min Act: -0.1700

Data Index: 7436755 (Open Web Text)

Max Activating Token Index: 396

Text #3

Max Range: 3.2292. Min Range: -3.2292

Max Act: 3.1521. Min Act: -0.1700

Data Index: 3678034 (Open Web Text)

Max Activating Token Index: 273

Text #4

Max Range: 3.2292. Min Range: -3.2292

Max Act: 3.0413. Min Act: -0.1700

Data Index: 6807237 (Open Web Text)

Max Activating Token Index: 279

Text #5

Max Range: 3.2292. Min Range: -3.2292

Max Act: 3.0754. Min Act: -0.1700

Data Index: 4211130 (Open Web Text)

Max Activating Token Index: 93

Text #6

Max Range: 3.2292. Min Range: -3.2292

Max Act: 2.9952. Min Act: -0.1700

Data Index: 5396668 (Open Web Text)

Max Activating Token Index: 118

Text #7

Max Range: 3.2292. Min Range: -3.2292

Max Act: 2.9451. Min Act: -0.1700

Data Index: 6355090 (Open Web Text)

Max Activating Token Index: 109

Text #8

Max Range: 3.2292. Min Range: -3.2292

Max Act: 2.9247. Min Act: -0.1700

Data Index: 7297237 (Open Web Text)

Max Activating Token Index: 805

Text #9

Max Range: 3.2292. Min Range: -3.2292

Max Act: 2.9413. Min Act: -0.1700

Data Index: 22619 (Open Web Text)

Max Activating Token Index: 686

Text #10

Max Range: 3.2292. Min Range: -3.2292

Max Act: 2.9307. Min Act: -0.1700

Data Index: 2740684 (Open Web Text)

Max Activating Token Index: 554

Text #11

Max Range: 3.2292. Min Range: -3.2292

Max Act: 2.8903. Min Act: -0.1700

Data Index: 8454333 (Open Web Text)

Max Activating Token Index: 98

Text #12

Max Range: 3.2292. Min Range: -3.2292

Max Act: 2.8598. Min Act: -0.1700

Data Index: 6783663 (Open Web Text)

Max Activating Token Index: 320

Text #13

Max Range: 3.2292. Min Range: -3.2292

Max Act: 2.8831. Min Act: -0.1700

Data Index: 6741058 (Open Web Text)

Max Activating Token Index: 201

Text #14

Max Range: 3.2292. Min Range: -3.2292

Max Act: 2.8909. Min Act: -0.1700

Data Index: 3062039 (Open Web Text)

Max Activating Token Index: 629

Text #15

Max Range: 3.2292. Min Range: -3.2292

Max Act: 2.8938. Min Act: -0.1700

Data Index: 1699021 (Open Web Text)

Max Activating Token Index: 73

Text #16

Max Range: 3.2292. Min Range: -3.2292

Max Act: 2.8532. Min Act: -0.1700

Data Index: 8152865 (Open Web Text)

Max Activating Token Index: 342

Text #17

Max Range: 3.2292. Min Range: -3.2292

Max Act: 2.8261. Min Act: -0.1700

Data Index: 6350643 (Open Web Text)

Max Activating Token Index: 282

Text #18

Max Range: 3.2292. Min Range: -3.2292

Max Act: 2.8295. Min Act: -0.1700

Data Index: 8069627 (Open Web Text)

Max Activating Token Index: 218

Text #19

Max Range: 3.2292. Min Range: -3.2292

Max Act: 2.8103. Min Act: -0.1700

Data Index: 3681848 (Open Web Text)

Max Activating Token Index: 1020