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

Dataset: Open Web Text

Neuron 2765 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: 4.1995. Min Range: -4.1995

Max Act: 4.1995. Min Act: -0.1700

Data Index: 6307096 (Open Web Text)

Max Activating Token Index: 617

Text #1

Max Range: 4.1995. Min Range: -4.1995

Max Act: 4.1007. Min Act: -0.1700

Data Index: 4044643 (Open Web Text)

Max Activating Token Index: 905

Text #2

Max Range: 4.1995. Min Range: -4.1995

Max Act: 4.0765. Min Act: -0.1700

Data Index: 7467059 (Open Web Text)

Max Activating Token Index: 274

Text #3

Max Range: 4.1995. Min Range: -4.1995

Max Act: 4.0785. Min Act: -0.1700

Data Index: 1212378 (Open Web Text)

Max Activating Token Index: 917

Text #4

Max Range: 4.1995. Min Range: -4.1995

Max Act: 4.0464. Min Act: -0.1700

Data Index: 8602562 (Open Web Text)

Max Activating Token Index: 278

Text #5

Max Range: 4.1995. Min Range: -4.1995

Max Act: 4.0875. Min Act: -0.1700

Data Index: 2399370 (Open Web Text)

Max Activating Token Index: 612

Text #6

Max Range: 4.1995. Min Range: -4.1995

Max Act: 4.0549. Min Act: -0.1700

Data Index: 8162305 (Open Web Text)

Max Activating Token Index: 614

Text #7

Max Range: 4.1995. Min Range: -4.1995

Max Act: 4.0565. Min Act: -0.1700

Data Index: 3052185 (Open Web Text)

Max Activating Token Index: 933

Text #8

Max Range: 4.1995. Min Range: -4.1995

Max Act: 4.0449. Min Act: -0.1700

Data Index: 8758798 (Open Web Text)

Max Activating Token Index: 479

Text #9

Max Range: 4.1995. Min Range: -4.1995

Max Act: 4.0318. Min Act: -0.1700

Data Index: 5578528 (Open Web Text)

Max Activating Token Index: 465

Text #10

Max Range: 4.1995. Min Range: -4.1995

Max Act: 4.0196. Min Act: -0.1700

Data Index: 7416309 (Open Web Text)

Max Activating Token Index: 630

Text #11

Max Range: 4.1995. Min Range: -4.1995

Max Act: 3.9930. Min Act: -0.1700

Data Index: 3601074 (Open Web Text)

Max Activating Token Index: 727

Text #12

Max Range: 4.1995. Min Range: -4.1995

Max Act: 3.9876. Min Act: -0.1700

Data Index: 1904559 (Open Web Text)

Max Activating Token Index: 715

Text #13

Max Range: 4.1995. Min Range: -4.1995

Max Act: 4.0097. Min Act: -0.1700

Data Index: 5807713 (Open Web Text)

Max Activating Token Index: 546

Text #14

Max Range: 4.1995. Min Range: -4.1995

Max Act: 3.9972. Min Act: -0.1700

Data Index: 3070236 (Open Web Text)

Max Activating Token Index: 926

Text #15

Max Range: 4.1995. Min Range: -4.1995

Max Act: 4.0204. Min Act: -0.1700

Data Index: 5024820 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.1995. Min Range: -4.1995

Max Act: 3.9861. Min Act: -0.1700

Data Index: 7731177 (Open Web Text)

Max Activating Token Index: 980

Text #17

Max Range: 4.1995. Min Range: -4.1995

Max Act: 3.9575. Min Act: -0.1700

Data Index: 5773682 (Open Web Text)

Max Activating Token Index: 802

Text #18

Max Range: 4.1995. Min Range: -4.1995

Max Act: 3.9556. Min Act: -0.1700

Data Index: 8141019 (Open Web Text)

Max Activating Token Index: 583

Text #19

Max Range: 4.1995. Min Range: -4.1995

Max Act: 3.9682. Min Act: -0.1700

Data Index: 221062 (Open Web Text)

Max Activating Token Index: 57