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

Dataset: Open Web Text

Neuron 394 in Layer 2

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: 5.2630. Min Range: -5.2630

Max Act: 5.2630. Min Act: -0.1700

Data Index: 4164204 (Open Web Text)

Max Activating Token Index: 95

Text #1

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.2136. Min Act: -0.1700

Data Index: 8209600 (Open Web Text)

Max Activating Token Index: 514

Text #2

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.2235. Min Act: -0.1700

Data Index: 5146442 (Open Web Text)

Max Activating Token Index: 139

Text #3

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.1162. Min Act: -0.1700

Data Index: 6395714 (Open Web Text)

Max Activating Token Index: 754

Text #4

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.0606. Min Act: -0.1700

Data Index: 6510798 (Open Web Text)

Max Activating Token Index: 13

Text #5

Max Range: 5.2630. Min Range: -5.2630

Max Act: 4.9909. Min Act: -0.1700

Data Index: 979945 (Open Web Text)

Max Activating Token Index: 70

Text #6

Max Range: 5.2630. Min Range: -5.2630

Max Act: 4.9630. Min Act: -0.1700

Data Index: 8400248 (Open Web Text)

Max Activating Token Index: 228

Text #7

Max Range: 5.2630. Min Range: -5.2630

Max Act: 4.9275. Min Act: -0.1700

Data Index: 5552596 (Open Web Text)

Max Activating Token Index: 933

Text #8

Max Range: 5.2630. Min Range: -5.2630

Max Act: 4.9099. Min Act: -0.1700

Data Index: 2329060 (Open Web Text)

Max Activating Token Index: 257

Text #9

Max Range: 5.2630. Min Range: -5.2630

Max Act: 4.9520. Min Act: -0.1700

Data Index: 658011 (Open Web Text)

Max Activating Token Index: 87

Text #10

Max Range: 5.2630. Min Range: -5.2630

Max Act: 4.9126. Min Act: -0.1700

Data Index: 660212 (Open Web Text)

Max Activating Token Index: 94

Text #11

Max Range: 5.2630. Min Range: -5.2630

Max Act: 4.9120. Min Act: -0.1700

Data Index: 5648566 (Open Web Text)

Max Activating Token Index: 225

Text #12

Max Range: 5.2630. Min Range: -5.2630

Max Act: 4.8993. Min Act: -0.1700

Data Index: 3776868 (Open Web Text)

Max Activating Token Index: 59

Text #13

Max Range: 5.2630. Min Range: -5.2630

Max Act: 4.9065. Min Act: -0.1700

Data Index: 6735204 (Open Web Text)

Max Activating Token Index: 63

Text #14

Max Range: 5.2630. Min Range: -5.2630

Max Act: 4.8866. Min Act: -0.1700

Data Index: 5859920 (Open Web Text)

Max Activating Token Index: 419

Text #15

Max Range: 5.2630. Min Range: -5.2630

Max Act: 4.8577. Min Act: -0.1700

Data Index: 2409285 (Open Web Text)

Max Activating Token Index: 36

Text #16

Max Range: 5.2630. Min Range: -5.2630

Max Act: 4.8266. Min Act: -0.1700

Data Index: 5037736 (Open Web Text)

Max Activating Token Index: 34

Text #17

Max Range: 5.2630. Min Range: -5.2630

Max Act: 4.8363. Min Act: -0.1700

Data Index: 829640 (Open Web Text)

Max Activating Token Index: 13

Text #18

Max Range: 5.2630. Min Range: -5.2630

Max Act: 4.8172. Min Act: -0.1700

Data Index: 6431201 (Open Web Text)

Max Activating Token Index: 102

Text #19

Max Range: 5.2630. Min Range: -5.2630

Max Act: 4.8491. Min Act: -0.1700

Data Index: 5178531 (Open Web Text)

Max Activating Token Index: 410