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

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

Neuron 672 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: 4.1044. Min Range: -4.1044

Max Act: 4.1044. Min Act: -0.1700

Data Index: 85034 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 4.1044. Min Range: -4.1044

Max Act: 4.0763. Min Act: -0.1700

Data Index: 1000213 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 4.1044. Min Range: -4.1044

Max Act: 4.0359. Min Act: -0.1700

Data Index: 1168924 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 4.1044. Min Range: -4.1044

Max Act: 4.0406. Min Act: -0.1700

Data Index: 493639 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 4.1044. Min Range: -4.1044

Max Act: 4.0731. Min Act: -0.1700

Data Index: 1084487 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 4.1044. Min Range: -4.1044

Max Act: 4.0331. Min Act: -0.1700

Data Index: 878329 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 4.1044. Min Range: -4.1044

Max Act: 4.0382. Min Act: -0.1700

Data Index: 11535 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 4.1044. Min Range: -4.1044

Max Act: 4.0469. Min Act: -0.1700

Data Index: 959606 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 4.1044. Min Range: -4.1044

Max Act: 4.0464. Min Act: -0.1700

Data Index: 156380 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 4.1044. Min Range: -4.1044

Max Act: 4.0152. Min Act: -0.1700

Data Index: 942949 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 4.1044. Min Range: -4.1044

Max Act: 3.9638. Min Act: -0.1700

Data Index: 321607 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 4.1044. Min Range: -4.1044

Max Act: 3.9600. Min Act: -0.1700

Data Index: 476798 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 4.1044. Min Range: -4.1044

Max Act: 3.9390. Min Act: -0.1700

Data Index: 419927 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 4.1044. Min Range: -4.1044

Max Act: 3.9351. Min Act: -0.1700

Data Index: 71517 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 4.1044. Min Range: -4.1044

Max Act: 3.9507. Min Act: -0.1700

Data Index: 67142 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 4.1044. Min Range: -4.1044

Max Act: 3.9548. Min Act: -0.1700

Data Index: 875310 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 4.1044. Min Range: -4.1044

Max Act: 3.9174. Min Act: -0.1700

Data Index: 1196565 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 4.1044. Min Range: -4.1044

Max Act: 3.9377. Min Act: -0.1700

Data Index: 128579 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 4.1044. Min Range: -4.1044

Max Act: 3.9483. Min Act: -0.1700

Data Index: 1280228 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 4.1044. Min Range: -4.1044

Max Act: 3.9364. Min Act: -0.1700

Data Index: 1128354 (C4 (Web Text))

Max Activating Token Index: 872