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

Dataset: Open Web Text

Neuron 2637 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: 4.7318. Min Range: -4.7318

Max Act: 4.7318. Min Act: -0.1700

Data Index: 8135505 (Open Web Text)

Max Activating Token Index: 152

Text #1

Max Range: 4.7318. Min Range: -4.7318

Max Act: 4.7005. Min Act: -0.1700

Data Index: 2229273 (Open Web Text)

Max Activating Token Index: 569

Text #2

Max Range: 4.7318. Min Range: -4.7318

Max Act: 4.6250. Min Act: -0.1700

Data Index: 557437 (Open Web Text)

Max Activating Token Index: 233

Text #3

Max Range: 4.7318. Min Range: -4.7318

Max Act: 4.5558. Min Act: -0.1700

Data Index: 5982479 (Open Web Text)

Max Activating Token Index: 184

Text #4

Max Range: 4.7318. Min Range: -4.7318

Max Act: 4.5404. Min Act: -0.1700

Data Index: 4618449 (Open Web Text)

Max Activating Token Index: 211

Text #5

Max Range: 4.7318. Min Range: -4.7318

Max Act: 4.5333. Min Act: -0.1700

Data Index: 6204029 (Open Web Text)

Max Activating Token Index: 414

Text #6

Max Range: 4.7318. Min Range: -4.7318

Max Act: 4.5221. Min Act: -0.1700

Data Index: 8692413 (Open Web Text)

Max Activating Token Index: 724

Text #7

Max Range: 4.7318. Min Range: -4.7318

Max Act: 4.5617. Min Act: -0.1700

Data Index: 502719 (Open Web Text)

Max Activating Token Index: 127

Text #8

Max Range: 4.7318. Min Range: -4.7318

Max Act: 4.5314. Min Act: -0.1700

Data Index: 1547171 (Open Web Text)

Max Activating Token Index: 241

Text #9

Max Range: 4.7318. Min Range: -4.7318

Max Act: 4.5329. Min Act: -0.1700

Data Index: 612501 (Open Web Text)

Max Activating Token Index: 60

Text #10

Max Range: 4.7318. Min Range: -4.7318

Max Act: 4.4072. Min Act: -0.1700

Data Index: 3697069 (Open Web Text)

Max Activating Token Index: 582

Text #11

Max Range: 4.7318. Min Range: -4.7318

Max Act: 4.5021. Min Act: -0.1700

Data Index: 7068596 (Open Web Text)

Max Activating Token Index: 825

Text #12

Max Range: 4.7318. Min Range: -4.7318

Max Act: 4.4087. Min Act: -0.1700

Data Index: 8408129 (Open Web Text)

Max Activating Token Index: 421

Text #13

Max Range: 4.7318. Min Range: -4.7318

Max Act: 4.4546. Min Act: -0.1700

Data Index: 1158089 (Open Web Text)

Max Activating Token Index: 154

Text #14

Max Range: 4.7318. Min Range: -4.7318

Max Act: 4.4271. Min Act: -0.1700

Data Index: 3968096 (Open Web Text)

Max Activating Token Index: 88

Text #15

Max Range: 4.7318. Min Range: -4.7318

Max Act: 4.4127. Min Act: -0.1700

Data Index: 6402901 (Open Web Text)

Max Activating Token Index: 171

Text #16

Max Range: 4.7318. Min Range: -4.7318

Max Act: 4.4169. Min Act: -0.1700

Data Index: 8775732 (Open Web Text)

Max Activating Token Index: 387

Text #17

Max Range: 4.7318. Min Range: -4.7318

Max Act: 4.4401. Min Act: -0.1700

Data Index: 3505162 (Open Web Text)

Max Activating Token Index: 359

Text #18

Max Range: 4.7318. Min Range: -4.7318

Max Act: 4.3647. Min Act: -0.1700

Data Index: 6558585 (Open Web Text)

Max Activating Token Index: 362

Text #19

Max Range: 4.7318. Min Range: -4.7318

Max Act: 4.3755. Min Act: -0.1700

Data Index: 3697123 (Open Web Text)

Max Activating Token Index: 641