Model: GELU Model: 1 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1700 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.0050. Min Range: -3.0050

Max Act: 3.0050. Min Act: -0.1700

Data Index: 635356 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 3.0050. Min Range: -3.0050

Max Act: 2.9521. Min Act: -0.1700

Data Index: 1303933 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 3.0050. Min Range: -3.0050

Max Act: 2.8527. Min Act: -0.1699

Data Index: 158124 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 3.0050. Min Range: -3.0050

Max Act: 2.8320. Min Act: -0.1700

Data Index: 858526 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 3.0050. Min Range: -3.0050

Max Act: 2.8296. Min Act: -0.1700

Data Index: 671993 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 3.0050. Min Range: -3.0050

Max Act: 2.8305. Min Act: -0.1700

Data Index: 1315940 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 3.0050. Min Range: -3.0050

Max Act: 2.8427. Min Act: -0.1700

Data Index: 849273 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 3.0050. Min Range: -3.0050

Max Act: 2.8291. Min Act: -0.1700

Data Index: 802760 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 3.0050. Min Range: -3.0050

Max Act: 2.8394. Min Act: -0.1700

Data Index: 166880 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 3.0050. Min Range: -3.0050

Max Act: 2.8160. Min Act: -0.1700

Data Index: 1062758 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 3.0050. Min Range: -3.0050

Max Act: 2.8023. Min Act: -0.1699

Data Index: 664506 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 3.0050. Min Range: -3.0050

Max Act: 2.8028. Min Act: -0.1700

Data Index: 1164709 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 3.0050. Min Range: -3.0050

Max Act: 2.8110. Min Act: -0.1700

Data Index: 280047 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 3.0050. Min Range: -3.0050

Max Act: 2.8040. Min Act: -0.1700

Data Index: 970683 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 3.0050. Min Range: -3.0050

Max Act: 2.7981. Min Act: -0.1700

Data Index: 1070189 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 3.0050. Min Range: -3.0050

Max Act: 2.7602. Min Act: -0.1700

Data Index: 1050359 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 3.0050. Min Range: -3.0050

Max Act: 2.7741. Min Act: -0.1700

Data Index: 1150126 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 3.0050. Min Range: -3.0050

Max Act: 2.7796. Min Act: -0.1700

Data Index: 1004493 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 3.0050. Min Range: -3.0050

Max Act: 2.7482. Min Act: -0.1700

Data Index: 1062475 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 3.0050. Min Range: -3.0050

Max Act: 2.7505. Min Act: -0.1700

Data Index: 895697 (C4 (Web Text))

Max Activating Token Index: 298