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

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

Neuron 216 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: 3.9247. Min Range: -3.9247

Max Act: 3.9247. Min Act: -0.1700

Data Index: 316272 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 3.9247. Min Range: -3.9247

Max Act: 3.8633. Min Act: -0.1700

Data Index: 616304 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 3.9247. Min Range: -3.9247

Max Act: 3.8175. Min Act: -0.1700

Data Index: 1219632 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 3.9247. Min Range: -3.9247

Max Act: 3.8362. Min Act: -0.1700

Data Index: 442520 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 3.9247. Min Range: -3.9247

Max Act: 3.8077. Min Act: -0.1700

Data Index: 958312 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 3.9247. Min Range: -3.9247

Max Act: 3.8328. Min Act: -0.1700

Data Index: 918695 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 3.9247. Min Range: -3.9247

Max Act: 3.7781. Min Act: -0.1700

Data Index: 1277314 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 3.9247. Min Range: -3.9247

Max Act: 3.7823. Min Act: -0.1700

Data Index: 847122 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 3.9247. Min Range: -3.9247

Max Act: 3.8028. Min Act: -0.1700

Data Index: 714803 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 3.9247. Min Range: -3.9247

Max Act: 3.7564. Min Act: -0.1700

Data Index: 696026 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 3.9247. Min Range: -3.9247

Max Act: 3.7740. Min Act: -0.1700

Data Index: 722593 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 3.9247. Min Range: -3.9247

Max Act: 3.7320. Min Act: -0.1700

Data Index: 1335501 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 3.9247. Min Range: -3.9247

Max Act: 3.6954. Min Act: -0.1700

Data Index: 847298 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 3.9247. Min Range: -3.9247

Max Act: 3.7338. Min Act: -0.1700

Data Index: 901771 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 3.9247. Min Range: -3.9247

Max Act: 3.7464. Min Act: -0.1700

Data Index: 741197 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 3.9247. Min Range: -3.9247

Max Act: 3.6974. Min Act: -0.1700

Data Index: 739724 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 3.9247. Min Range: -3.9247

Max Act: 3.7328. Min Act: -0.1700

Data Index: 522072 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 3.9247. Min Range: -3.9247

Max Act: 3.6403. Min Act: -0.1700

Data Index: 975056 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 3.9247. Min Range: -3.9247

Max Act: 3.6332. Min Act: -0.1700

Data Index: 568687 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 3.9247. Min Range: -3.9247

Max Act: 3.6348. Min Act: -0.1700

Data Index: 1108777 (C4 (Web Text))

Max Activating Token Index: 973