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

Dataset: Open Web Text

Neuron 1084 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: 5.3235. Min Range: -5.3235

Max Act: 5.3235. Min Act: -0.1700

Data Index: 7123522 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 5.3235. Min Range: -5.3235

Max Act: 5.2961. Min Act: -0.1700

Data Index: 7093037 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.3235. Min Range: -5.3235

Max Act: 5.2844. Min Act: -0.1700

Data Index: 4552372 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 5.3235. Min Range: -5.3235

Max Act: 5.2597. Min Act: -0.1700

Data Index: 735738 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 5.3235. Min Range: -5.3235

Max Act: 5.2597. Min Act: -0.1700

Data Index: 1064762 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 5.3235. Min Range: -5.3235

Max Act: 5.2597. Min Act: -0.1700

Data Index: 1229830 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 5.3235. Min Range: -5.3235

Max Act: 5.2344. Min Act: -0.1700

Data Index: 7413515 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 5.3235. Min Range: -5.3235

Max Act: 5.2438. Min Act: -0.1700

Data Index: 5967596 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 5.3235. Min Range: -5.3235

Max Act: 5.2373. Min Act: -0.1700

Data Index: 4552382 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 5.3235. Min Range: -5.3235

Max Act: 5.2285. Min Act: -0.1700

Data Index: 7123521 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 5.3235. Min Range: -5.3235

Max Act: 5.2312. Min Act: -0.1700

Data Index: 3202084 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 5.3235. Min Range: -5.3235

Max Act: 5.2446. Min Act: -0.1700

Data Index: 7123518 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 5.3235. Min Range: -5.3235

Max Act: 5.1908. Min Act: -0.1700

Data Index: 3553823 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 5.3235. Min Range: -5.3235

Max Act: 5.2108. Min Act: -0.1700

Data Index: 8253418 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 5.3235. Min Range: -5.3235

Max Act: 5.2108. Min Act: -0.1700

Data Index: 5690643 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 5.3235. Min Range: -5.3235

Max Act: 5.1944. Min Act: -0.1700

Data Index: 4004740 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 5.3235. Min Range: -5.3235

Max Act: 5.1530. Min Act: -0.1700

Data Index: 7123524 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 5.3235. Min Range: -5.3235

Max Act: 5.1467. Min Act: -0.1700

Data Index: 7123520 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 5.3235. Min Range: -5.3235

Max Act: 5.1690. Min Act: -0.1700

Data Index: 7123523 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 5.3235. Min Range: -5.3235

Max Act: 5.1513. Min Act: -0.1700

Data Index: 7813569 (Open Web Text)

Max Activating Token Index: 3