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

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

Neuron 969 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: 4.4946. Min Range: -4.4946

Max Act: 4.4946. Min Act: -0.1700

Data Index: 1453558 (Python Code)

Max Activating Token Index: 937

Text #1

Max Range: 4.4946. Min Range: -4.4946

Max Act: 4.4613. Min Act: -0.1700

Data Index: 1637717 (Python Code)

Max Activating Token Index: 255

Text #2

Max Range: 4.4946. Min Range: -4.4946

Max Act: 4.4012. Min Act: -0.1700

Data Index: 301429 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 4.4946. Min Range: -4.4946

Max Act: 4.3586. Min Act: -0.1700

Data Index: 1082636 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 4.4946. Min Range: -4.4946

Max Act: 4.3700. Min Act: -0.1700

Data Index: 1543745 (Python Code)

Max Activating Token Index: 522

Text #5

Max Range: 4.4946. Min Range: -4.4946

Max Act: 4.3952. Min Act: -0.1700

Data Index: 1606804 (Python Code)

Max Activating Token Index: 470

Text #6

Max Range: 4.4946. Min Range: -4.4946

Max Act: 4.3537. Min Act: -0.1700

Data Index: 1109806 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 4.4946. Min Range: -4.4946

Max Act: 4.3766. Min Act: -0.1700

Data Index: 115290 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 4.4946. Min Range: -4.4946

Max Act: 4.2929. Min Act: -0.1700

Data Index: 1613810 (Python Code)

Max Activating Token Index: 724

Text #9

Max Range: 4.4946. Min Range: -4.4946

Max Act: 4.2229. Min Act: -0.1700

Data Index: 1366174 (Python Code)

Max Activating Token Index: 118

Text #10

Max Range: 4.4946. Min Range: -4.4946

Max Act: 4.1608. Min Act: -0.1700

Data Index: 1428839 (Python Code)

Max Activating Token Index: 137

Text #11

Max Range: 4.4946. Min Range: -4.4946

Max Act: 4.1870. Min Act: -0.1700

Data Index: 1546505 (Python Code)

Max Activating Token Index: 61

Text #12

Max Range: 4.4946. Min Range: -4.4946

Max Act: 4.1614. Min Act: -0.1700

Data Index: 1582669 (Python Code)

Max Activating Token Index: 609

Text #13

Max Range: 4.4946. Min Range: -4.4946

Max Act: 4.1227. Min Act: -0.1700

Data Index: 179237 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 4.4946. Min Range: -4.4946

Max Act: 4.0819. Min Act: -0.1700

Data Index: 1417223 (Python Code)

Max Activating Token Index: 500

Text #15

Max Range: 4.4946. Min Range: -4.4946

Max Act: 4.1167. Min Act: -0.1700

Data Index: 1437310 (Python Code)

Max Activating Token Index: 690

Text #16

Max Range: 4.4946. Min Range: -4.4946

Max Act: 4.0697. Min Act: -0.1700

Data Index: 1451712 (Python Code)

Max Activating Token Index: 652

Text #17

Max Range: 4.4946. Min Range: -4.4946

Max Act: 4.0379. Min Act: -0.1700

Data Index: 1500553 (Python Code)

Max Activating Token Index: 115

Text #18

Max Range: 4.4946. Min Range: -4.4946

Max Act: 4.0215. Min Act: -0.1700

Data Index: 1443855 (Python Code)

Max Activating Token Index: 351

Text #19

Max Range: 4.4946. Min Range: -4.4946

Max Act: 3.9895. Min Act: -0.1700

Data Index: 1594005 (Python Code)

Max Activating Token Index: 467