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

Dataset: Open Web Text

Neuron 249 in Layer 2

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: 2.4550. Min Range: -2.4550

Max Act: 2.4458. Min Act: -0.1700

Data Index: 5120249 (Open Web Text)

Max Activating Token Index: 977

Text #1

Max Range: 2.4550. Min Range: -2.4550

Max Act: 2.4550. Min Act: -0.1700

Data Index: 4172095 (Open Web Text)

Max Activating Token Index: 862

Text #2

Max Range: 2.4550. Min Range: -2.4550

Max Act: 2.3786. Min Act: -0.1700

Data Index: 3495295 (Open Web Text)

Max Activating Token Index: 627

Text #3

Max Range: 2.4550. Min Range: -2.4550

Max Act: 2.4207. Min Act: -0.1700

Data Index: 7592643 (Open Web Text)

Max Activating Token Index: 774

Text #4

Max Range: 2.4550. Min Range: -2.4550

Max Act: 2.3873. Min Act: -0.1700

Data Index: 8654093 (Open Web Text)

Max Activating Token Index: 200

Text #5

Max Range: 2.4550. Min Range: -2.4550

Max Act: 2.3853. Min Act: -0.1700

Data Index: 3057158 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.4550. Min Range: -2.4550

Max Act: 2.3598. Min Act: -0.1700

Data Index: 728020 (Open Web Text)

Max Activating Token Index: 975

Text #7

Max Range: 2.4550. Min Range: -2.4550

Max Act: 2.3566. Min Act: -0.1700

Data Index: 4949818 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.4550. Min Range: -2.4550

Max Act: 2.3543. Min Act: -0.1700

Data Index: 7654686 (Open Web Text)

Max Activating Token Index: 544

Text #9

Max Range: 2.4550. Min Range: -2.4550

Max Act: 2.3047. Min Act: -0.1700

Data Index: 436232 (Open Web Text)

Max Activating Token Index: 237

Text #10

Max Range: 2.4550. Min Range: -2.4550

Max Act: 2.3146. Min Act: -0.1700

Data Index: 7341498 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.4550. Min Range: -2.4550

Max Act: 2.3177. Min Act: -0.1700

Data Index: 18332 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 2.4550. Min Range: -2.4550

Max Act: 2.3119. Min Act: -0.1700

Data Index: 7963685 (Open Web Text)

Max Activating Token Index: 469

Text #13

Max Range: 2.4550. Min Range: -2.4550

Max Act: 2.3082. Min Act: -0.1700

Data Index: 6858890 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 2.4550. Min Range: -2.4550

Max Act: 2.2860. Min Act: -0.1700

Data Index: 1116265 (Open Web Text)

Max Activating Token Index: 690

Text #15

Max Range: 2.4550. Min Range: -2.4550

Max Act: 2.3000. Min Act: -0.1700

Data Index: 914729 (Open Web Text)

Max Activating Token Index: 79

Text #16

Max Range: 2.4550. Min Range: -2.4550

Max Act: 2.2930. Min Act: -0.1700

Data Index: 4486768 (Open Web Text)

Max Activating Token Index: 455

Text #17

Max Range: 2.4550. Min Range: -2.4550

Max Act: 2.2812. Min Act: -0.1700

Data Index: 6623242 (Open Web Text)

Max Activating Token Index: 305

Text #18

Max Range: 2.4550. Min Range: -2.4550

Max Act: 2.2589. Min Act: -0.1700

Data Index: 6244152 (Open Web Text)

Max Activating Token Index: 820

Text #19

Max Range: 2.4550. Min Range: -2.4550

Max Act: 2.2811. Min Act: -0.1700

Data Index: 1483918 (Open Web Text)

Max Activating Token Index: 4