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

Dataset: Open Web Text

Neuron 700 in Layer 1

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: 5.4356. Min Range: -5.4356

Max Act: 5.4356. Min Act: -0.1700

Data Index: 3111274 (Open Web Text)

Max Activating Token Index: 67

Text #1

Max Range: 5.4356. Min Range: -5.4356

Max Act: 5.3833. Min Act: -0.1700

Data Index: 6407433 (Open Web Text)

Max Activating Token Index: 416

Text #2

Max Range: 5.4356. Min Range: -5.4356

Max Act: 5.3628. Min Act: -0.1700

Data Index: 3526243 (Open Web Text)

Max Activating Token Index: 899

Text #3

Max Range: 5.4356. Min Range: -5.4356

Max Act: 5.3395. Min Act: -0.1700

Data Index: 5500336 (Open Web Text)

Max Activating Token Index: 93

Text #4

Max Range: 5.4356. Min Range: -5.4356

Max Act: 5.3292. Min Act: -0.1700

Data Index: 2812094 (Open Web Text)

Max Activating Token Index: 42

Text #5

Max Range: 5.4356. Min Range: -5.4356

Max Act: 5.3069. Min Act: -0.1700

Data Index: 2056212 (Open Web Text)

Max Activating Token Index: 84

Text #6

Max Range: 5.4356. Min Range: -5.4356

Max Act: 5.3120. Min Act: -0.1700

Data Index: 7714003 (Open Web Text)

Max Activating Token Index: 767

Text #7

Max Range: 5.4356. Min Range: -5.4356

Max Act: 5.3040. Min Act: -0.1700

Data Index: 8671494 (Open Web Text)

Max Activating Token Index: 242

Text #8

Max Range: 5.4356. Min Range: -5.4356

Max Act: 5.2647. Min Act: -0.1700

Data Index: 6027201 (Open Web Text)

Max Activating Token Index: 45

Text #9

Max Range: 5.4356. Min Range: -5.4356

Max Act: 5.2751. Min Act: -0.1700

Data Index: 2248941 (Open Web Text)

Max Activating Token Index: 653

Text #10

Max Range: 5.4356. Min Range: -5.4356

Max Act: 5.2647. Min Act: -0.1700

Data Index: 8495000 (Open Web Text)

Max Activating Token Index: 309

Text #11

Max Range: 5.4356. Min Range: -5.4356

Max Act: 5.2835. Min Act: -0.1700

Data Index: 8629355 (Open Web Text)

Max Activating Token Index: 105

Text #12

Max Range: 5.4356. Min Range: -5.4356

Max Act: 5.2631. Min Act: -0.1700

Data Index: 2040199 (Open Web Text)

Max Activating Token Index: 950

Text #13

Max Range: 5.4356. Min Range: -5.4356

Max Act: 5.2642. Min Act: -0.1700

Data Index: 3048775 (Open Web Text)

Max Activating Token Index: 783

Text #14

Max Range: 5.4356. Min Range: -5.4356

Max Act: 5.2643. Min Act: -0.1700

Data Index: 935643 (Open Web Text)

Max Activating Token Index: 32

Text #15

Max Range: 5.4356. Min Range: -5.4356

Max Act: 5.2989. Min Act: -0.1700

Data Index: 8372244 (Open Web Text)

Max Activating Token Index: 106

Text #16

Max Range: 5.4356. Min Range: -5.4356

Max Act: 5.2693. Min Act: -0.1700

Data Index: 4007562 (Open Web Text)

Max Activating Token Index: 619

Text #17

Max Range: 5.4356. Min Range: -5.4356

Max Act: 5.2899. Min Act: -0.1700

Data Index: 8812618 (Open Web Text)

Max Activating Token Index: 808

Text #18

Max Range: 5.4356. Min Range: -5.4356

Max Act: 5.2735. Min Act: -0.1700

Data Index: 8207598 (Open Web Text)

Max Activating Token Index: 62

Text #19

Max Range: 5.4356. Min Range: -5.4356

Max Act: 5.2433. Min Act: -0.1700

Data Index: 8345786 (Open Web Text)

Max Activating Token Index: 788