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

Dataset: Open Web Text

Neuron 2901 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: 4.8295. Min Range: -4.8295

Max Act: 4.8295. Min Act: -0.1700

Data Index: 1668630 (Open Web Text)

Max Activating Token Index: 836

Text #1

Max Range: 4.8295. Min Range: -4.8295

Max Act: 4.5810. Min Act: -0.1700

Data Index: 1340550 (Open Web Text)

Max Activating Token Index: 39

Text #2

Max Range: 4.8295. Min Range: -4.8295

Max Act: 4.5004. Min Act: -0.1700

Data Index: 4223898 (Open Web Text)

Max Activating Token Index: 692

Text #3

Max Range: 4.8295. Min Range: -4.8295

Max Act: 4.4713. Min Act: -0.1700

Data Index: 6684444 (Open Web Text)

Max Activating Token Index: 707

Text #4

Max Range: 4.8295. Min Range: -4.8295

Max Act: 4.4365. Min Act: -0.1700

Data Index: 7838672 (Open Web Text)

Max Activating Token Index: 27

Text #5

Max Range: 4.8295. Min Range: -4.8295

Max Act: 4.4122. Min Act: -0.1700

Data Index: 4830169 (Open Web Text)

Max Activating Token Index: 187

Text #6

Max Range: 4.8295. Min Range: -4.8295

Max Act: 4.3650. Min Act: -0.1700

Data Index: 1555747 (Open Web Text)

Max Activating Token Index: 149

Text #7

Max Range: 4.8295. Min Range: -4.8295

Max Act: 4.3398. Min Act: -0.1700

Data Index: 4106119 (Open Web Text)

Max Activating Token Index: 401

Text #8

Max Range: 4.8295. Min Range: -4.8295

Max Act: 4.3976. Min Act: -0.1700

Data Index: 5178757 (Open Web Text)

Max Activating Token Index: 430

Text #9

Max Range: 4.8295. Min Range: -4.8295

Max Act: 4.3446. Min Act: -0.1700

Data Index: 5088206 (Open Web Text)

Max Activating Token Index: 445

Text #10

Max Range: 4.8295. Min Range: -4.8295

Max Act: 4.3382. Min Act: -0.1700

Data Index: 1651003 (Open Web Text)

Max Activating Token Index: 114

Text #11

Max Range: 4.8295. Min Range: -4.8295

Max Act: 4.3565. Min Act: -0.1700

Data Index: 6897269 (Open Web Text)

Max Activating Token Index: 74

Text #12

Max Range: 4.8295. Min Range: -4.8295

Max Act: 4.3165. Min Act: -0.1700

Data Index: 6073701 (Open Web Text)

Max Activating Token Index: 927

Text #13

Max Range: 4.8295. Min Range: -4.8295

Max Act: 4.2908. Min Act: -0.1700

Data Index: 1289546 (Open Web Text)

Max Activating Token Index: 142

Text #14

Max Range: 4.8295. Min Range: -4.8295

Max Act: 4.3462. Min Act: -0.1700

Data Index: 1826892 (Open Web Text)

Max Activating Token Index: 202

Text #15

Max Range: 4.8295. Min Range: -4.8295

Max Act: 4.2663. Min Act: -0.1700

Data Index: 2643434 (Open Web Text)

Max Activating Token Index: 957

Text #16

Max Range: 4.8295. Min Range: -4.8295

Max Act: 4.2609. Min Act: -0.1700

Data Index: 1879535 (Open Web Text)

Max Activating Token Index: 463

Text #17

Max Range: 4.8295. Min Range: -4.8295

Max Act: 4.2307. Min Act: -0.1700

Data Index: 5035338 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 4.8295. Min Range: -4.8295

Max Act: 4.1950. Min Act: -0.1700

Data Index: 4219568 (Open Web Text)

Max Activating Token Index: 64

Text #19

Max Range: 4.8295. Min Range: -4.8295

Max Act: 4.2096. Min Act: -0.1700

Data Index: 2790605 (Open Web Text)

Max Activating Token Index: 1007