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

Dataset: Open Web Text

Neuron 257 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: 4.6046. Min Range: -4.6046

Max Act: 4.5429. Min Act: -0.1700

Data Index: 5762801 (Open Web Text)

Max Activating Token Index: 488

Text #1

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.6046. Min Act: -0.1700

Data Index: 1055918 (Open Web Text)

Max Activating Token Index: 348

Text #2

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.5232. Min Act: -0.1700

Data Index: 4189319 (Open Web Text)

Max Activating Token Index: 705

Text #3

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.4908. Min Act: -0.1700

Data Index: 8390960 (Open Web Text)

Max Activating Token Index: 86

Text #4

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.4827. Min Act: -0.1700

Data Index: 6095011 (Open Web Text)

Max Activating Token Index: 371

Text #5

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.4603. Min Act: -0.1700

Data Index: 5431433 (Open Web Text)

Max Activating Token Index: 469

Text #6

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.4662. Min Act: -0.1700

Data Index: 8260541 (Open Web Text)

Max Activating Token Index: 233

Text #7

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.4153. Min Act: -0.1700

Data Index: 5117448 (Open Web Text)

Max Activating Token Index: 699

Text #8

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.4341. Min Act: -0.1700

Data Index: 4840229 (Open Web Text)

Max Activating Token Index: 72

Text #9

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.4294. Min Act: -0.1700

Data Index: 3053821 (Open Web Text)

Max Activating Token Index: 836

Text #10

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.4338. Min Act: -0.1700

Data Index: 8012341 (Open Web Text)

Max Activating Token Index: 171

Text #11

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.4148. Min Act: -0.1700

Data Index: 5517970 (Open Web Text)

Max Activating Token Index: 959

Text #12

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.4095. Min Act: -0.1700

Data Index: 3055969 (Open Web Text)

Max Activating Token Index: 319

Text #13

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.3940. Min Act: -0.1700

Data Index: 7221589 (Open Web Text)

Max Activating Token Index: 91

Text #14

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.3942. Min Act: -0.1700

Data Index: 8383497 (Open Web Text)

Max Activating Token Index: 594

Text #15

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.3731. Min Act: -0.1700

Data Index: 7169998 (Open Web Text)

Max Activating Token Index: 195

Text #16

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.4060. Min Act: -0.1700

Data Index: 5150859 (Open Web Text)

Max Activating Token Index: 477

Text #17

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.4019. Min Act: -0.1700

Data Index: 4378070 (Open Web Text)

Max Activating Token Index: 693

Text #18

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.4517. Min Act: -0.1700

Data Index: 6279364 (Open Web Text)

Max Activating Token Index: 1016

Text #19

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.3981. Min Act: -0.1700

Data Index: 2034251 (Open Web Text)

Max Activating Token Index: 722