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

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

Neuron 797 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: 3.0448. Min Range: -3.0448

Max Act: 3.0160. Min Act: -0.1700

Data Index: 196957 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 3.0448. Min Range: -3.0448

Max Act: 3.0027. Min Act: -0.1700

Data Index: 980324 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 3.0448. Min Range: -3.0448

Max Act: 3.0448. Min Act: -0.1700

Data Index: 883113 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.9774. Min Act: -0.1700

Data Index: 417471 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.9821. Min Act: -0.1700

Data Index: 240798 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.9593. Min Act: -0.1700

Data Index: 1127530 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.9602. Min Act: -0.1700

Data Index: 2299 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.9662. Min Act: -0.1700

Data Index: 1337595 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.9418. Min Act: -0.1700

Data Index: 871628 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.9258. Min Act: -0.1700

Data Index: 219062 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.9400. Min Act: -0.1700

Data Index: 281515 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.9405. Min Act: -0.1700

Data Index: 696987 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.9351. Min Act: -0.1700

Data Index: 754875 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.9271. Min Act: -0.1700

Data Index: 1245748 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.9639. Min Act: -0.1700

Data Index: 1338352 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.9517. Min Act: -0.1700

Data Index: 659981 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.9193. Min Act: -0.1700

Data Index: 271582 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.9321. Min Act: -0.1700

Data Index: 949854 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.9339. Min Act: -0.1700

Data Index: 458620 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 3.0448. Min Range: -3.0448

Max Act: 2.9138. Min Act: -0.1700

Data Index: 491905 (C4 (Web Text))

Max Activating Token Index: 120