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

Dataset: Open Web Text

Neuron 2906 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: 3.7208. Min Range: -3.7208

Max Act: 3.7208. Min Act: -0.1700

Data Index: 3615043 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 3.7208. Min Range: -3.7208

Max Act: 3.6798. Min Act: -0.1700

Data Index: 3790097 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.7208. Min Range: -3.7208

Max Act: 3.6203. Min Act: -0.1700

Data Index: 6866066 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 3.7208. Min Range: -3.7208

Max Act: 3.5897. Min Act: -0.1700

Data Index: 4061020 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.7208. Min Range: -3.7208

Max Act: 3.5577. Min Act: -0.1700

Data Index: 1135477 (Open Web Text)

Max Activating Token Index: 439

Text #5

Max Range: 3.7208. Min Range: -3.7208

Max Act: 3.5282. Min Act: -0.1700

Data Index: 84070 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 3.7208. Min Range: -3.7208

Max Act: 3.5373. Min Act: -0.1700

Data Index: 503093 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 3.7208. Min Range: -3.7208

Max Act: 3.5103. Min Act: -0.1700

Data Index: 2282519 (Open Web Text)

Max Activating Token Index: 51

Text #8

Max Range: 3.7208. Min Range: -3.7208

Max Act: 3.5212. Min Act: -0.1700

Data Index: 5787899 (Open Web Text)

Max Activating Token Index: 303

Text #9

Max Range: 3.7208. Min Range: -3.7208

Max Act: 3.5115. Min Act: -0.1700

Data Index: 7143030 (Open Web Text)

Max Activating Token Index: 496

Text #10

Max Range: 3.7208. Min Range: -3.7208

Max Act: 3.4978. Min Act: -0.1700

Data Index: 1375197 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.7208. Min Range: -3.7208

Max Act: 3.4978. Min Act: -0.1700

Data Index: 8399329 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.7208. Min Range: -3.7208

Max Act: 3.4978. Min Act: -0.1700

Data Index: 5883387 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.7208. Min Range: -3.7208

Max Act: 3.4978. Min Act: -0.1700

Data Index: 6103081 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.7208. Min Range: -3.7208

Max Act: 3.4587. Min Act: -0.1700

Data Index: 6575421 (Open Web Text)

Max Activating Token Index: 836

Text #15

Max Range: 3.7208. Min Range: -3.7208

Max Act: 3.4889. Min Act: -0.1700

Data Index: 4081331 (Open Web Text)

Max Activating Token Index: 501

Text #16

Max Range: 3.7208. Min Range: -3.7208

Max Act: 3.4765. Min Act: -0.1700

Data Index: 6264066 (Open Web Text)

Max Activating Token Index: 36

Text #17

Max Range: 3.7208. Min Range: -3.7208

Max Act: 3.4532. Min Act: -0.1700

Data Index: 3893468 (Open Web Text)

Max Activating Token Index: 871

Text #18

Max Range: 3.7208. Min Range: -3.7208

Max Act: 3.4369. Min Act: -0.1700

Data Index: 8280068 (Open Web Text)

Max Activating Token Index: 101

Text #19

Max Range: 3.7208. Min Range: -3.7208

Max Act: 3.4358. Min Act: -0.1700

Data Index: 5566055 (Open Web Text)

Max Activating Token Index: 380