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

Dataset: Open Web Text

Neuron 667 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: 3.8172. Min Range: -3.8172

Max Act: 3.7820. Min Act: -0.1700

Data Index: 711005 (Open Web Text)

Max Activating Token Index: 242

Text #1

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.8172. Min Act: -0.1700

Data Index: 4587113 (Open Web Text)

Max Activating Token Index: 390

Text #2

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.7620. Min Act: -0.1700

Data Index: 6572902 (Open Web Text)

Max Activating Token Index: 73

Text #3

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.7442. Min Act: -0.1700

Data Index: 6080821 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.7387. Min Act: -0.1700

Data Index: 7304548 (Open Web Text)

Max Activating Token Index: 949

Text #5

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.7178. Min Act: -0.1700

Data Index: 7471619 (Open Web Text)

Max Activating Token Index: 362

Text #6

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.7158. Min Act: -0.1700

Data Index: 1138299 (Open Web Text)

Max Activating Token Index: 652

Text #7

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6860. Min Act: -0.1700

Data Index: 1096376 (Open Web Text)

Max Activating Token Index: 268

Text #8

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6500. Min Act: -0.1700

Data Index: 6054396 (Open Web Text)

Max Activating Token Index: 626

Text #9

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6949. Min Act: -0.1700

Data Index: 5022139 (Open Web Text)

Max Activating Token Index: 92

Text #10

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6876. Min Act: -0.1700

Data Index: 5992877 (Open Web Text)

Max Activating Token Index: 826

Text #11

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6871. Min Act: -0.1700

Data Index: 3144470 (Open Web Text)

Max Activating Token Index: 445

Text #12

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6292. Min Act: -0.1700

Data Index: 6834892 (Open Web Text)

Max Activating Token Index: 642

Text #13

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6615. Min Act: -0.1700

Data Index: 7060309 (Open Web Text)

Max Activating Token Index: 27

Text #14

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6333. Min Act: -0.1700

Data Index: 6797844 (Open Web Text)

Max Activating Token Index: 951

Text #15

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6603. Min Act: -0.1700

Data Index: 5174957 (Open Web Text)

Max Activating Token Index: 527

Text #16

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6104. Min Act: -0.1700

Data Index: 4131838 (Open Web Text)

Max Activating Token Index: 32

Text #17

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6247. Min Act: -0.1700

Data Index: 2208880 (Open Web Text)

Max Activating Token Index: 493

Text #18

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6127. Min Act: -0.1700

Data Index: 5623647 (Open Web Text)

Max Activating Token Index: 918

Text #19

Max Range: 3.8172. Min Range: -3.8172

Max Act: 3.6114. Min Act: -0.1700

Data Index: 6294538 (Open Web Text)

Max Activating Token Index: 24