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

Dataset: Open Web Text

Neuron 1336 in Layer 5

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: 3.7207. Min Range: -3.7207

Max Act: 3.6900. Min Act: -0.1700

Data Index: 1672486 (Open Web Text)

Max Activating Token Index: 132

Text #1

Max Range: 3.7207. Min Range: -3.7207

Max Act: 3.7207. Min Act: -0.1700

Data Index: 6576025 (Open Web Text)

Max Activating Token Index: 993

Text #2

Max Range: 3.7207. Min Range: -3.7207

Max Act: 3.6420. Min Act: -0.1700

Data Index: 633751 (Open Web Text)

Max Activating Token Index: 232

Text #3

Max Range: 3.7207. Min Range: -3.7207

Max Act: 3.6161. Min Act: -0.1700

Data Index: 4345789 (Open Web Text)

Max Activating Token Index: 88

Text #4

Max Range: 3.7207. Min Range: -3.7207

Max Act: 3.6181. Min Act: -0.1700

Data Index: 5642152 (Open Web Text)

Max Activating Token Index: 28

Text #5

Max Range: 3.7207. Min Range: -3.7207

Max Act: 3.6192. Min Act: -0.1700

Data Index: 3582854 (Open Web Text)

Max Activating Token Index: 442

Text #6

Max Range: 3.7207. Min Range: -3.7207

Max Act: 3.6384. Min Act: -0.1700

Data Index: 6233025 (Open Web Text)

Max Activating Token Index: 964

Text #7

Max Range: 3.7207. Min Range: -3.7207

Max Act: 3.6027. Min Act: -0.1700

Data Index: 8402675 (Open Web Text)

Max Activating Token Index: 1006

Text #8

Max Range: 3.7207. Min Range: -3.7207

Max Act: 3.5886. Min Act: -0.1700

Data Index: 7587703 (Open Web Text)

Max Activating Token Index: 297

Text #9

Max Range: 3.7207. Min Range: -3.7207

Max Act: 3.5890. Min Act: -0.1700

Data Index: 2342819 (Open Web Text)

Max Activating Token Index: 276

Text #10

Max Range: 3.7207. Min Range: -3.7207

Max Act: 3.5657. Min Act: -0.1700

Data Index: 7585740 (Open Web Text)

Max Activating Token Index: 229

Text #11

Max Range: 3.7207. Min Range: -3.7207

Max Act: 3.5999. Min Act: -0.1700

Data Index: 4211404 (Open Web Text)

Max Activating Token Index: 197

Text #12

Max Range: 3.7207. Min Range: -3.7207

Max Act: 3.5635. Min Act: -0.1700

Data Index: 8294830 (Open Web Text)

Max Activating Token Index: 177

Text #13

Max Range: 3.7207. Min Range: -3.7207

Max Act: 3.5541. Min Act: -0.1700

Data Index: 2972344 (Open Web Text)

Max Activating Token Index: 174

Text #14

Max Range: 3.7207. Min Range: -3.7207

Max Act: 3.5937. Min Act: -0.1700

Data Index: 8296311 (Open Web Text)

Max Activating Token Index: 952

Text #15

Max Range: 3.7207. Min Range: -3.7207

Max Act: 3.5839. Min Act: -0.1700

Data Index: 8808177 (Open Web Text)

Max Activating Token Index: 624

Text #16

Max Range: 3.7207. Min Range: -3.7207

Max Act: 3.5635. Min Act: -0.1700

Data Index: 7126517 (Open Web Text)

Max Activating Token Index: 83

Text #17

Max Range: 3.7207. Min Range: -3.7207

Max Act: 3.5685. Min Act: -0.1700

Data Index: 429939 (Open Web Text)

Max Activating Token Index: 281

Text #18

Max Range: 3.7207. Min Range: -3.7207

Max Act: 3.5955. Min Act: -0.1700

Data Index: 8099784 (Open Web Text)

Max Activating Token Index: 667

Text #19

Max Range: 3.7207. Min Range: -3.7207

Max Act: 3.5743. Min Act: -0.1700

Data Index: 5107437 (Open Web Text)

Max Activating Token Index: 915