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

Dataset: Open Web Text

Neuron 1951 in Layer 0

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: 3.3968. Min Range: -3.3968

Max Act: 3.3968. Min Act: -0.1700

Data Index: 3122822 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3588. Min Act: -0.1700

Data Index: 5433845 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3577. Min Act: -0.1700

Data Index: 8249560 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3678. Min Act: -0.1700

Data Index: 1829378 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3302. Min Act: -0.1700

Data Index: 5883157 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3595. Min Act: -0.1700

Data Index: 4054734 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3482. Min Act: -0.1700

Data Index: 3188490 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3515. Min Act: -0.1700

Data Index: 1020205 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3332. Min Act: -0.1700

Data Index: 338174 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3497. Min Act: -0.1700

Data Index: 2575586 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3158. Min Act: -0.1700

Data Index: 2209891 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2931. Min Act: -0.1700

Data Index: 5142022 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3184. Min Act: -0.1700

Data Index: 1802532 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2956. Min Act: -0.1700

Data Index: 1846831 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3132. Min Act: -0.1700

Data Index: 1717730 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3091. Min Act: -0.1700

Data Index: 3240318 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3053. Min Act: -0.1700

Data Index: 4451882 (Open Web Text)

Max Activating Token Index: 14

Text #17

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2947. Min Act: -0.1700

Data Index: 7625653 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2936. Min Act: -0.1700

Data Index: 3560589 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2906. Min Act: -0.1700

Data Index: 2550678 (Open Web Text)

Max Activating Token Index: 7