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

Dataset: Open Web Text

Neuron 704 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: 3.7535. Min Range: -3.7535

Max Act: 3.7535. Min Act: -0.1700

Data Index: 4316112 (Open Web Text)

Max Activating Token Index: 275

Text #1

Max Range: 3.7535. Min Range: -3.7535

Max Act: 3.6775. Min Act: -0.1700

Data Index: 3149061 (Open Web Text)

Max Activating Token Index: 503

Text #2

Max Range: 3.7535. Min Range: -3.7535

Max Act: 3.6839. Min Act: -0.1700

Data Index: 1756340 (Open Web Text)

Max Activating Token Index: 412

Text #3

Max Range: 3.7535. Min Range: -3.7535

Max Act: 3.6434. Min Act: -0.1700

Data Index: 8155422 (Open Web Text)

Max Activating Token Index: 267

Text #4

Max Range: 3.7535. Min Range: -3.7535

Max Act: 3.6396. Min Act: -0.1700

Data Index: 1050366 (Open Web Text)

Max Activating Token Index: 468

Text #5

Max Range: 3.7535. Min Range: -3.7535

Max Act: 3.6300. Min Act: -0.1700

Data Index: 8132956 (Open Web Text)

Max Activating Token Index: 569

Text #6

Max Range: 3.7535. Min Range: -3.7535

Max Act: 3.5895. Min Act: -0.1700

Data Index: 4538031 (Open Web Text)

Max Activating Token Index: 525

Text #7

Max Range: 3.7535. Min Range: -3.7535

Max Act: 3.5807. Min Act: -0.1700

Data Index: 3423314 (Open Web Text)

Max Activating Token Index: 593

Text #8

Max Range: 3.7535. Min Range: -3.7535

Max Act: 3.5728. Min Act: -0.1700

Data Index: 2812248 (Open Web Text)

Max Activating Token Index: 19

Text #9

Max Range: 3.7535. Min Range: -3.7535

Max Act: 3.5904. Min Act: -0.1700

Data Index: 7831164 (Open Web Text)

Max Activating Token Index: 112

Text #10

Max Range: 3.7535. Min Range: -3.7535

Max Act: 3.5727. Min Act: -0.1700

Data Index: 8027813 (Open Web Text)

Max Activating Token Index: 831

Text #11

Max Range: 3.7535. Min Range: -3.7535

Max Act: 3.5756. Min Act: -0.1700

Data Index: 1522552 (Open Web Text)

Max Activating Token Index: 108

Text #12

Max Range: 3.7535. Min Range: -3.7535

Max Act: 3.5515. Min Act: -0.1700

Data Index: 4569736 (Open Web Text)

Max Activating Token Index: 815

Text #13

Max Range: 3.7535. Min Range: -3.7535

Max Act: 3.5670. Min Act: -0.1700

Data Index: 6280564 (Open Web Text)

Max Activating Token Index: 59

Text #14

Max Range: 3.7535. Min Range: -3.7535

Max Act: 3.5699. Min Act: -0.1700

Data Index: 3311673 (Open Web Text)

Max Activating Token Index: 163

Text #15

Max Range: 3.7535. Min Range: -3.7535

Max Act: 3.5297. Min Act: -0.1700

Data Index: 6656284 (Open Web Text)

Max Activating Token Index: 932

Text #16

Max Range: 3.7535. Min Range: -3.7535

Max Act: 3.5419. Min Act: -0.1700

Data Index: 8794235 (Open Web Text)

Max Activating Token Index: 485

Text #17

Max Range: 3.7535. Min Range: -3.7535

Max Act: 3.5179. Min Act: -0.1700

Data Index: 626492 (Open Web Text)

Max Activating Token Index: 541

Text #18

Max Range: 3.7535. Min Range: -3.7535

Max Act: 3.5139. Min Act: -0.1700

Data Index: 2695284 (Open Web Text)

Max Activating Token Index: 601

Text #19

Max Range: 3.7535. Min Range: -3.7535

Max Act: 3.5285. Min Act: -0.1700

Data Index: 1623716 (Open Web Text)

Max Activating Token Index: 369