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

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

Neuron 1479 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: 3.6035. Min Range: -3.6035

Max Act: 3.6035. Min Act: -0.1699

Data Index: 739499 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.5967. Min Act: -0.1699

Data Index: 425842 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.5747. Min Act: -0.1699

Data Index: 1152443 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.5739. Min Act: -0.1700

Data Index: 538525 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.5556. Min Act: -0.1519

Data Index: 191667 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.5425. Min Act: -0.1700

Data Index: 103276 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.5408. Min Act: -0.1692

Data Index: 1138047 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.5343. Min Act: -0.1699

Data Index: 661205 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.5255. Min Act: -0.1699

Data Index: 667087 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.5260. Min Act: -0.1700

Data Index: 450368 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.4687. Min Act: -0.1700

Data Index: 202609 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.4683. Min Act: -0.1699

Data Index: 148505 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.4534. Min Act: -0.1700

Data Index: 453969 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.4529. Min Act: -0.1700

Data Index: 1482814 (Python Code)

Max Activating Token Index: 15

Text #14

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.4508. Min Act: -0.1614

Data Index: 1353061 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.4258. Min Act: -0.1699

Data Index: 998416 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.4346. Min Act: -0.1678

Data Index: 1007769 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.4451. Min Act: -0.1700

Data Index: 47790 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.4371. Min Act: -0.1690

Data Index: 661489 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 3.6035. Min Range: -3.6035

Max Act: 3.4125. Min Act: -0.1700

Data Index: 571125 (C4 (Web Text))

Max Activating Token Index: 166