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

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

Neuron 482 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: 2.9028. Min Range: -2.9028

Max Act: 2.9028. Min Act: -0.1700

Data Index: 689705 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.7023. Min Act: -0.1700

Data Index: 311375 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.6544. Min Act: -0.1700

Data Index: 1397188 (Python Code)

Max Activating Token Index: 459

Text #3

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.6327. Min Act: -0.1700

Data Index: 1593441 (Python Code)

Max Activating Token Index: 25

Text #4

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.6515. Min Act: -0.1700

Data Index: 1429256 (Python Code)

Max Activating Token Index: 490

Text #5

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.6194. Min Act: -0.1700

Data Index: 1489936 (Python Code)

Max Activating Token Index: 576

Text #6

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.6178. Min Act: -0.1700

Data Index: 1235254 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.6030. Min Act: -0.1700

Data Index: 1229139 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.6200. Min Act: -0.1700

Data Index: 1338365 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.5978. Min Act: -0.1700

Data Index: 1191054 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.6131. Min Act: -0.1700

Data Index: 237532 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.5849. Min Act: -0.1700

Data Index: 223558 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.5766. Min Act: -0.1700

Data Index: 1136159 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.5582. Min Act: -0.1700

Data Index: 1398444 (Python Code)

Max Activating Token Index: 240

Text #14

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.5485. Min Act: -0.1700

Data Index: 1399981 (Python Code)

Max Activating Token Index: 997

Text #15

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.5160. Min Act: -0.1700

Data Index: 3770 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.5174. Min Act: -0.1700

Data Index: 1654324 (Python Code)

Max Activating Token Index: 612

Text #17

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.5057. Min Act: -0.1700

Data Index: 64332 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.5117. Min Act: -0.1700

Data Index: 910775 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.5177. Min Act: -0.1700

Data Index: 75250 (C4 (Web Text))

Max Activating Token Index: 16