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

Dataset: Open Web Text

Neuron 414 in Layer 5

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: 4.8477. Min Range: -4.8477

Max Act: 4.8477. Min Act: -0.1700

Data Index: 3110551 (Open Web Text)

Max Activating Token Index: 127

Text #1

Max Range: 4.8477. Min Range: -4.8477

Max Act: 4.7009. Min Act: -0.1700

Data Index: 719804 (Open Web Text)

Max Activating Token Index: 134

Text #2

Max Range: 4.8477. Min Range: -4.8477

Max Act: 4.7257. Min Act: -0.1700

Data Index: 6159938 (Open Web Text)

Max Activating Token Index: 496

Text #3

Max Range: 4.8477. Min Range: -4.8477

Max Act: 4.6715. Min Act: -0.1700

Data Index: 6698947 (Open Web Text)

Max Activating Token Index: 517

Text #4

Max Range: 4.8477. Min Range: -4.8477

Max Act: 4.6677. Min Act: -0.1700

Data Index: 8430115 (Open Web Text)

Max Activating Token Index: 1014

Text #5

Max Range: 4.8477. Min Range: -4.8477

Max Act: 4.6649. Min Act: -0.1700

Data Index: 4984354 (Open Web Text)

Max Activating Token Index: 844

Text #6

Max Range: 4.8477. Min Range: -4.8477

Max Act: 4.6232. Min Act: -0.1700

Data Index: 1159537 (Open Web Text)

Max Activating Token Index: 844

Text #7

Max Range: 4.8477. Min Range: -4.8477

Max Act: 4.6353. Min Act: -0.1700

Data Index: 6618948 (Open Web Text)

Max Activating Token Index: 136

Text #8

Max Range: 4.8477. Min Range: -4.8477

Max Act: 4.6098. Min Act: -0.1700

Data Index: 8811528 (Open Web Text)

Max Activating Token Index: 628

Text #9

Max Range: 4.8477. Min Range: -4.8477

Max Act: 4.6051. Min Act: -0.1700

Data Index: 3717739 (Open Web Text)

Max Activating Token Index: 620

Text #10

Max Range: 4.8477. Min Range: -4.8477

Max Act: 4.5713. Min Act: -0.1700

Data Index: 2262057 (Open Web Text)

Max Activating Token Index: 398

Text #11

Max Range: 4.8477. Min Range: -4.8477

Max Act: 4.5933. Min Act: -0.1700

Data Index: 3790676 (Open Web Text)

Max Activating Token Index: 948

Text #12

Max Range: 4.8477. Min Range: -4.8477

Max Act: 4.5979. Min Act: -0.1700

Data Index: 5033823 (Open Web Text)

Max Activating Token Index: 753

Text #13

Max Range: 4.8477. Min Range: -4.8477

Max Act: 4.5417. Min Act: -0.1700

Data Index: 7695747 (Open Web Text)

Max Activating Token Index: 53

Text #14

Max Range: 4.8477. Min Range: -4.8477

Max Act: 4.5117. Min Act: -0.1700

Data Index: 3231297 (Open Web Text)

Max Activating Token Index: 343

Text #15

Max Range: 4.8477. Min Range: -4.8477

Max Act: 4.5370. Min Act: -0.1700

Data Index: 4627650 (Open Web Text)

Max Activating Token Index: 692

Text #16

Max Range: 4.8477. Min Range: -4.8477

Max Act: 4.5355. Min Act: -0.1700

Data Index: 7203342 (Open Web Text)

Max Activating Token Index: 902

Text #17

Max Range: 4.8477. Min Range: -4.8477

Max Act: 4.4990. Min Act: -0.1700

Data Index: 4733558 (Open Web Text)

Max Activating Token Index: 507

Text #18

Max Range: 4.8477. Min Range: -4.8477

Max Act: 4.4932. Min Act: -0.1700

Data Index: 6642229 (Open Web Text)

Max Activating Token Index: 304

Text #19

Max Range: 4.8477. Min Range: -4.8477

Max Act: 4.4841. Min Act: -0.1700

Data Index: 452485 (Open Web Text)

Max Activating Token Index: 823