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

Dataset: Open Web Text

Neuron 1559 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: 4.2615. Min Range: -4.2615

Max Act: 4.2615. Min Act: -0.1700

Data Index: 1257011 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 4.2615. Min Range: -4.2615

Max Act: 4.2505. Min Act: -0.1700

Data Index: 8590995 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.2615. Min Range: -4.2615

Max Act: 4.2218. Min Act: -0.1700

Data Index: 7908214 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.2615. Min Range: -4.2615

Max Act: 4.2303. Min Act: -0.1700

Data Index: 3877013 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 4.2615. Min Range: -4.2615

Max Act: 4.2055. Min Act: -0.1700

Data Index: 6272958 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 4.2615. Min Range: -4.2615

Max Act: 4.1586. Min Act: -0.1700

Data Index: 417610 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.2615. Min Range: -4.2615

Max Act: 4.1410. Min Act: -0.1700

Data Index: 1030956 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.2615. Min Range: -4.2615

Max Act: 4.1397. Min Act: -0.1700

Data Index: 3134439 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.2615. Min Range: -4.2615

Max Act: 4.1238. Min Act: -0.1700

Data Index: 3982464 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.2615. Min Range: -4.2615

Max Act: 4.0994. Min Act: -0.1700

Data Index: 6444430 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 4.2615. Min Range: -4.2615

Max Act: 4.0946. Min Act: -0.1700

Data Index: 1193231 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.2615. Min Range: -4.2615

Max Act: 4.0981. Min Act: -0.1700

Data Index: 983851 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.2615. Min Range: -4.2615

Max Act: 4.1148. Min Act: -0.1700

Data Index: 1790007 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 4.2615. Min Range: -4.2615

Max Act: 4.1156. Min Act: -0.1700

Data Index: 6239586 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.2615. Min Range: -4.2615

Max Act: 4.0994. Min Act: -0.1700

Data Index: 5885203 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 4.2615. Min Range: -4.2615

Max Act: 4.0933. Min Act: -0.1700

Data Index: 4680829 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.2615. Min Range: -4.2615

Max Act: 4.1018. Min Act: -0.1700

Data Index: 543050 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 4.2615. Min Range: -4.2615

Max Act: 4.0744. Min Act: -0.1699

Data Index: 2900817 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 4.2615. Min Range: -4.2615

Max Act: 4.0731. Min Act: -0.1700

Data Index: 1196489 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.2615. Min Range: -4.2615

Max Act: 4.0607. Min Act: -0.1700

Data Index: 4414035 (Open Web Text)

Max Activating Token Index: 25