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

Dataset: Open Web Text

Neuron 1715 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: 1.5592. Min Range: -1.5592

Max Act: 1.5592. Min Act: -0.1700

Data Index: 7878048 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.5426. Min Act: -0.1700

Data Index: 379624 (Open Web Text)

Max Activating Token Index: 860

Text #2

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.5524. Min Act: -0.1700

Data Index: 3402306 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.5454. Min Act: -0.1699

Data Index: 7933529 (Open Web Text)

Max Activating Token Index: 21

Text #4

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.5321. Min Act: -0.1700

Data Index: 3865897 (Open Web Text)

Max Activating Token Index: 895

Text #5

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.5356. Min Act: -0.1700

Data Index: 8272972 (Open Web Text)

Max Activating Token Index: 986

Text #6

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.5328. Min Act: -0.1698

Data Index: 3794845 (Open Web Text)

Max Activating Token Index: 519

Text #7

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.5099. Min Act: -0.1700

Data Index: 7267009 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.5095. Min Act: -0.1700

Data Index: 4503122 (Open Web Text)

Max Activating Token Index: 92

Text #9

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.5069. Min Act: -0.1700

Data Index: 435844 (Open Web Text)

Max Activating Token Index: 18

Text #10

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.4999. Min Act: -0.1700

Data Index: 4043761 (Open Web Text)

Max Activating Token Index: 78

Text #11

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.4913. Min Act: -0.1678

Data Index: 7247852 (Open Web Text)

Max Activating Token Index: 451

Text #12

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.4920. Min Act: -0.1700

Data Index: 6996334 (Open Web Text)

Max Activating Token Index: 137

Text #13

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.4945. Min Act: -0.1700

Data Index: 5073016 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.4859. Min Act: -0.1700

Data Index: 4907404 (Open Web Text)

Max Activating Token Index: 474

Text #15

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.4856. Min Act: -0.1700

Data Index: 4520283 (Open Web Text)

Max Activating Token Index: 455

Text #16

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.4859. Min Act: -0.1699

Data Index: 668374 (Open Web Text)

Max Activating Token Index: 199

Text #17

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.4932. Min Act: -0.1700

Data Index: 2617214 (Open Web Text)

Max Activating Token Index: 949

Text #18

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.4898. Min Act: -0.1700

Data Index: 5293411 (Open Web Text)

Max Activating Token Index: 60

Text #19

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.4857. Min Act: -0.1699

Data Index: 6415357 (Open Web Text)

Max Activating Token Index: 540