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

Dataset: Open Web Text

Neuron 1648 in Layer 6

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: 3.5841. Min Range: -3.5841

Max Act: 3.5841. Min Act: -0.1700

Data Index: 4223354 (Open Web Text)

Max Activating Token Index: 925

Text #1

Max Range: 3.5841. Min Range: -3.5841

Max Act: 3.5838. Min Act: -0.1700

Data Index: 4464633 (Open Web Text)

Max Activating Token Index: 880

Text #2

Max Range: 3.5841. Min Range: -3.5841

Max Act: 3.5308. Min Act: -0.1700

Data Index: 2874254 (Open Web Text)

Max Activating Token Index: 827

Text #3

Max Range: 3.5841. Min Range: -3.5841

Max Act: 3.5252. Min Act: -0.1700

Data Index: 5393727 (Open Web Text)

Max Activating Token Index: 453

Text #4

Max Range: 3.5841. Min Range: -3.5841

Max Act: 3.5326. Min Act: -0.1700

Data Index: 6118997 (Open Web Text)

Max Activating Token Index: 408

Text #5

Max Range: 3.5841. Min Range: -3.5841

Max Act: 3.5401. Min Act: -0.1700

Data Index: 4287724 (Open Web Text)

Max Activating Token Index: 54

Text #6

Max Range: 3.5841. Min Range: -3.5841

Max Act: 3.5288. Min Act: -0.1700

Data Index: 947966 (Open Web Text)

Max Activating Token Index: 249

Text #7

Max Range: 3.5841. Min Range: -3.5841

Max Act: 3.5258. Min Act: -0.1700

Data Index: 6104378 (Open Web Text)

Max Activating Token Index: 647

Text #8

Max Range: 3.5841. Min Range: -3.5841

Max Act: 3.5164. Min Act: -0.1700

Data Index: 2551501 (Open Web Text)

Max Activating Token Index: 361

Text #9

Max Range: 3.5841. Min Range: -3.5841

Max Act: 3.5055. Min Act: -0.1700

Data Index: 3325240 (Open Web Text)

Max Activating Token Index: 672

Text #10

Max Range: 3.5841. Min Range: -3.5841

Max Act: 3.4795. Min Act: -0.1700

Data Index: 7779781 (Open Web Text)

Max Activating Token Index: 715

Text #11

Max Range: 3.5841. Min Range: -3.5841

Max Act: 3.4531. Min Act: -0.1700

Data Index: 1655976 (Open Web Text)

Max Activating Token Index: 951

Text #12

Max Range: 3.5841. Min Range: -3.5841

Max Act: 3.4314. Min Act: -0.1700

Data Index: 1689448 (Open Web Text)

Max Activating Token Index: 366

Text #13

Max Range: 3.5841. Min Range: -3.5841

Max Act: 3.4379. Min Act: -0.1700

Data Index: 8476336 (Open Web Text)

Max Activating Token Index: 875

Text #14

Max Range: 3.5841. Min Range: -3.5841

Max Act: 3.4334. Min Act: -0.1700

Data Index: 2411545 (Open Web Text)

Max Activating Token Index: 468

Text #15

Max Range: 3.5841. Min Range: -3.5841

Max Act: 3.4256. Min Act: -0.1700

Data Index: 4603489 (Open Web Text)

Max Activating Token Index: 541

Text #16

Max Range: 3.5841. Min Range: -3.5841

Max Act: 3.3898. Min Act: -0.1700

Data Index: 5799017 (Open Web Text)

Max Activating Token Index: 853

Text #17

Max Range: 3.5841. Min Range: -3.5841

Max Act: 3.4076. Min Act: -0.1700

Data Index: 3038073 (Open Web Text)

Max Activating Token Index: 63

Text #18

Max Range: 3.5841. Min Range: -3.5841

Max Act: 3.4253. Min Act: -0.1700

Data Index: 3280052 (Open Web Text)

Max Activating Token Index: 444

Text #19

Max Range: 3.5841. Min Range: -3.5841

Max Act: 3.4163. Min Act: -0.1700

Data Index: 6207910 (Open Web Text)

Max Activating Token Index: 448