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

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

Neuron 298 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: 4.0321. Min Range: -4.0321

Max Act: 4.0321. Min Act: -0.1700

Data Index: 1123454 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.8847. Min Act: -0.1700

Data Index: 530730 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.6963. Min Act: -0.1700

Data Index: 1073460 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.7036. Min Act: -0.1700

Data Index: 341231 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.6348. Min Act: -0.1700

Data Index: 176415 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.6177. Min Act: -0.1700

Data Index: 1263159 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.5980. Min Act: -0.1700

Data Index: 534361 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.6032. Min Act: -0.1700

Data Index: 710456 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.6109. Min Act: -0.1700

Data Index: 1116561 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.5984. Min Act: -0.1700

Data Index: 884193 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.5754. Min Act: -0.1700

Data Index: 1229815 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.5600. Min Act: -0.1700

Data Index: 1349023 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.5693. Min Act: -0.1700

Data Index: 202428 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.5808. Min Act: -0.1700

Data Index: 1007092 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.5833. Min Act: -0.1700

Data Index: 491531 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.5458. Min Act: -0.1700

Data Index: 428362 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.5512. Min Act: -0.1700

Data Index: 90833 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.5559. Min Act: -0.1700

Data Index: 458119 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.5445. Min Act: -0.1700

Data Index: 183440 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 4.0321. Min Range: -4.0321

Max Act: 3.5389. Min Act: -0.1700

Data Index: 269449 (C4 (Web Text))

Max Activating Token Index: 213