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

Dataset: Open Web Text

Neuron 73 in Layer 2

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: 3.0520. Min Range: -3.0520

Max Act: 3.0520. Min Act: -0.1700

Data Index: 6576531 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.0520. Min Range: -3.0520

Max Act: 3.0408. Min Act: -0.1700

Data Index: 5636192 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.0520. Min Range: -3.0520

Max Act: 3.0261. Min Act: -0.1700

Data Index: 6019372 (Open Web Text)

Max Activating Token Index: 854

Text #3

Max Range: 3.0520. Min Range: -3.0520

Max Act: 2.9603. Min Act: -0.1700

Data Index: 3851808 (Open Web Text)

Max Activating Token Index: 37

Text #4

Max Range: 3.0520. Min Range: -3.0520

Max Act: 2.9559. Min Act: -0.1700

Data Index: 6088173 (Open Web Text)

Max Activating Token Index: 24

Text #5

Max Range: 3.0520. Min Range: -3.0520

Max Act: 2.9460. Min Act: -0.1700

Data Index: 6540255 (Open Web Text)

Max Activating Token Index: 424

Text #6

Max Range: 3.0520. Min Range: -3.0520

Max Act: 2.9253. Min Act: -0.1700

Data Index: 599250 (Open Web Text)

Max Activating Token Index: 241

Text #7

Max Range: 3.0520. Min Range: -3.0520

Max Act: 2.9569. Min Act: -0.1700

Data Index: 4711145 (Open Web Text)

Max Activating Token Index: 962

Text #8

Max Range: 3.0520. Min Range: -3.0520

Max Act: 2.9157. Min Act: -0.1700

Data Index: 8352406 (Open Web Text)

Max Activating Token Index: 512

Text #9

Max Range: 3.0520. Min Range: -3.0520

Max Act: 2.9305. Min Act: -0.1700

Data Index: 536915 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.0520. Min Range: -3.0520

Max Act: 2.9319. Min Act: -0.1700

Data Index: 5736014 (Open Web Text)

Max Activating Token Index: 107

Text #11

Max Range: 3.0520. Min Range: -3.0520

Max Act: 2.9018. Min Act: -0.1700

Data Index: 1748793 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.0520. Min Range: -3.0520

Max Act: 2.9009. Min Act: -0.1700

Data Index: 197460 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.0520. Min Range: -3.0520

Max Act: 2.8746. Min Act: -0.1700

Data Index: 4813279 (Open Web Text)

Max Activating Token Index: 919

Text #14

Max Range: 3.0520. Min Range: -3.0520

Max Act: 2.8995. Min Act: -0.1700

Data Index: 5539958 (Open Web Text)

Max Activating Token Index: 101

Text #15

Max Range: 3.0520. Min Range: -3.0520

Max Act: 2.8507. Min Act: -0.1700

Data Index: 4066380 (Open Web Text)

Max Activating Token Index: 21

Text #16

Max Range: 3.0520. Min Range: -3.0520

Max Act: 2.8862. Min Act: -0.1700

Data Index: 291499 (Open Web Text)

Max Activating Token Index: 152

Text #17

Max Range: 3.0520. Min Range: -3.0520

Max Act: 2.8740. Min Act: -0.1700

Data Index: 7931084 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.0520. Min Range: -3.0520

Max Act: 2.8670. Min Act: -0.1700

Data Index: 7795142 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.0520. Min Range: -3.0520

Max Act: 2.8914. Min Act: -0.1700

Data Index: 5902059 (Open Web Text)

Max Activating Token Index: 44