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

Dataset: Open Web Text

Neuron 1958 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: 3.0891. Min Range: -3.0891

Max Act: 3.0891. Min Act: -0.1700

Data Index: 1183079 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.0891. Min Range: -3.0891

Max Act: 3.0653. Min Act: -0.1700

Data Index: 8030379 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.0891. Min Range: -3.0891

Max Act: 3.0302. Min Act: -0.1700

Data Index: 4941107 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.0891. Min Range: -3.0891

Max Act: 3.0293. Min Act: -0.1700

Data Index: 2459042 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 3.0891. Min Range: -3.0891

Max Act: 3.0179. Min Act: -0.1700

Data Index: 6344091 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 3.0891. Min Range: -3.0891

Max Act: 3.0055. Min Act: -0.1700

Data Index: 7358372 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.0891. Min Range: -3.0891

Max Act: 3.0017. Min Act: -0.1700

Data Index: 2547666 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9852. Min Act: -0.1700

Data Index: 1968577 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9792. Min Act: -0.1700

Data Index: 473709 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9699. Min Act: -0.1700

Data Index: 6645145 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9532. Min Act: -0.1700

Data Index: 7690526 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9536. Min Act: -0.1700

Data Index: 620576 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9661. Min Act: -0.1700

Data Index: 1717080 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9262. Min Act: -0.1700

Data Index: 3773235 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9257. Min Act: -0.1700

Data Index: 5487429 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9234. Min Act: -0.1700

Data Index: 4595220 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9352. Min Act: -0.1700

Data Index: 5796846 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9356. Min Act: -0.1700

Data Index: 2644129 (Open Web Text)

Max Activating Token Index: 103

Text #18

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9250. Min Act: -0.1700

Data Index: 311178 (Open Web Text)

Max Activating Token Index: 821

Text #19

Max Range: 3.0891. Min Range: -3.0891

Max Act: 2.9203. Min Act: -0.1700

Data Index: 2124546 (Open Web Text)

Max Activating Token Index: 12