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

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

Neuron 1769 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: 5.0854. Min Range: -5.0854

Max Act: 5.0854. Min Act: -0.1700

Data Index: 418285 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 5.0854. Min Range: -5.0854

Max Act: 5.0402. Min Act: -0.1700

Data Index: 218907 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.9482. Min Act: -0.1700

Data Index: 827114 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.8269. Min Act: -0.1700

Data Index: 843597 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.8055. Min Act: -0.1700

Data Index: 482365 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.7386. Min Act: -0.1700

Data Index: 678317 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.7492. Min Act: -0.1700

Data Index: 164740 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.7324. Min Act: -0.1700

Data Index: 1097402 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.7141. Min Act: -0.1700

Data Index: 1053135 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.7351. Min Act: -0.1700

Data Index: 43099 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.7301. Min Act: -0.1700

Data Index: 951122 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.7121. Min Act: -0.1700

Data Index: 1117310 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.6673. Min Act: -0.1700

Data Index: 642122 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.6545. Min Act: -0.1700

Data Index: 1037677 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.6756. Min Act: -0.1700

Data Index: 132172 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.7170. Min Act: -0.1700

Data Index: 248770 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.6663. Min Act: -0.1700

Data Index: 156709 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.6370. Min Act: -0.1700

Data Index: 150904 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.6425. Min Act: -0.1700

Data Index: 659682 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.6375. Min Act: -0.1700

Data Index: 879845 (C4 (Web Text))

Max Activating Token Index: 327