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

Dataset: Open Web Text

Neuron 205 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: 3.6956. Min Range: -3.6956

Max Act: 3.6810. Min Act: -0.1700

Data Index: 6761138 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 3.6956. Min Range: -3.6956

Max Act: 3.6866. Min Act: -0.1700

Data Index: 4146185 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.6956. Min Range: -3.6956

Max Act: 3.6948. Min Act: -0.1700

Data Index: 6235921 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 3.6956. Min Range: -3.6956

Max Act: 3.6956. Min Act: -0.1700

Data Index: 5630339 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.6956. Min Range: -3.6956

Max Act: 3.6543. Min Act: -0.1700

Data Index: 6524200 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.6956. Min Range: -3.6956

Max Act: 3.6595. Min Act: -0.1700

Data Index: 997446 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.6956. Min Range: -3.6956

Max Act: 3.6688. Min Act: -0.1700

Data Index: 2446443 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.6956. Min Range: -3.6956

Max Act: 3.6612. Min Act: -0.1700

Data Index: 1937419 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.6956. Min Range: -3.6956

Max Act: 3.6688. Min Act: -0.1700

Data Index: 1365422 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.6956. Min Range: -3.6956

Max Act: 3.6296. Min Act: -0.1700

Data Index: 86250 (Open Web Text)

Max Activating Token Index: 38

Text #10

Max Range: 3.6956. Min Range: -3.6956

Max Act: 3.6253. Min Act: -0.1700

Data Index: 6456802 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.6956. Min Range: -3.6956

Max Act: 3.6167. Min Act: -0.1700

Data Index: 8702962 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.6956. Min Range: -3.6956

Max Act: 3.6345. Min Act: -0.1700

Data Index: 1216759 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.6956. Min Range: -3.6956

Max Act: 3.6190. Min Act: -0.1700

Data Index: 1648350 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.6956. Min Range: -3.6956

Max Act: 3.6013. Min Act: -0.1700

Data Index: 5661850 (Open Web Text)

Max Activating Token Index: 358

Text #15

Max Range: 3.6956. Min Range: -3.6956

Max Act: 3.6122. Min Act: -0.1700

Data Index: 902044 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.6956. Min Range: -3.6956

Max Act: 3.5931. Min Act: -0.1700

Data Index: 2488836 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.6956. Min Range: -3.6956

Max Act: 3.5986. Min Act: -0.1700

Data Index: 5701823 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 3.6956. Min Range: -3.6956

Max Act: 3.5859. Min Act: -0.1700

Data Index: 1945016 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.6956. Min Range: -3.6956

Max Act: 3.6085. Min Act: -0.1700

Data Index: 1965172 (Open Web Text)

Max Activating Token Index: 4