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

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

Neuron 1086 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: 3.3474. Min Range: -3.3474

Max Act: 3.3474. Min Act: -0.1700

Data Index: 757945 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.3410. Min Act: -0.1700

Data Index: 21751 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.3333. Min Act: -0.1700

Data Index: 1111308 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.3199. Min Act: -0.1700

Data Index: 143802 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.2987. Min Act: -0.1700

Data Index: 298685 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.2905. Min Act: -0.1700

Data Index: 33332 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.2796. Min Act: -0.1700

Data Index: 556713 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.2479. Min Act: -0.1700

Data Index: 1188654 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.2711. Min Act: -0.1700

Data Index: 337896 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.2794. Min Act: -0.1700

Data Index: 1022317 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.2217. Min Act: -0.1700

Data Index: 466286 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.2584. Min Act: -0.1700

Data Index: 739421 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.2377. Min Act: -0.1700

Data Index: 87854 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.2493. Min Act: -0.1700

Data Index: 1028057 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.2408. Min Act: -0.1700

Data Index: 1247792 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.2107. Min Act: -0.1700

Data Index: 341757 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.2016. Min Act: -0.1700

Data Index: 320686 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.2403. Min Act: -0.1700

Data Index: 489317 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.2357. Min Act: -0.1700

Data Index: 598347 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.2388. Min Act: -0.1700

Data Index: 1060698 (C4 (Web Text))

Max Activating Token Index: 460