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

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

Neuron 1536 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: 4.5288. Min Range: -4.5288

Max Act: 4.5288. Min Act: -0.1700

Data Index: 1457026 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 4.5288. Min Range: -4.5288

Max Act: 4.4248. Min Act: -0.1700

Data Index: 611715 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 4.5288. Min Range: -4.5288

Max Act: 4.4205. Min Act: -0.1700

Data Index: 1203438 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 4.5288. Min Range: -4.5288

Max Act: 4.3789. Min Act: -0.1700

Data Index: 330858 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 4.5288. Min Range: -4.5288

Max Act: 4.3543. Min Act: -0.1700

Data Index: 1599171 (Python Code)

Max Activating Token Index: 270

Text #5

Max Range: 4.5288. Min Range: -4.5288

Max Act: 4.3213. Min Act: -0.1700

Data Index: 1239914 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 4.5288. Min Range: -4.5288

Max Act: 4.3408. Min Act: -0.1700

Data Index: 1651095 (Python Code)

Max Activating Token Index: 733

Text #7

Max Range: 4.5288. Min Range: -4.5288

Max Act: 4.3457. Min Act: -0.1700

Data Index: 1421567 (Python Code)

Max Activating Token Index: 534

Text #8

Max Range: 4.5288. Min Range: -4.5288

Max Act: 4.3363. Min Act: -0.1700

Data Index: 980760 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 4.5288. Min Range: -4.5288

Max Act: 4.3212. Min Act: -0.1700

Data Index: 805693 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 4.5288. Min Range: -4.5288

Max Act: 4.2671. Min Act: -0.1700

Data Index: 1505549 (Python Code)

Max Activating Token Index: 63

Text #11

Max Range: 4.5288. Min Range: -4.5288

Max Act: 4.2678. Min Act: -0.1700

Data Index: 458995 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 4.5288. Min Range: -4.5288

Max Act: 4.2428. Min Act: -0.1700

Data Index: 1230925 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 4.5288. Min Range: -4.5288

Max Act: 4.2488. Min Act: -0.1700

Data Index: 1276430 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 4.5288. Min Range: -4.5288

Max Act: 4.2396. Min Act: -0.1700

Data Index: 434858 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 4.5288. Min Range: -4.5288

Max Act: 4.2098. Min Act: -0.1700

Data Index: 350676 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 4.5288. Min Range: -4.5288

Max Act: 4.1782. Min Act: -0.1700

Data Index: 1361170 (Python Code)

Max Activating Token Index: 541

Text #17

Max Range: 4.5288. Min Range: -4.5288

Max Act: 4.1831. Min Act: -0.1700

Data Index: 412111 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 4.5288. Min Range: -4.5288

Max Act: 4.1978. Min Act: -0.1700

Data Index: 251478 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 4.5288. Min Range: -4.5288

Max Act: 4.1723. Min Act: -0.1700

Data Index: 1542990 (Python Code)

Max Activating Token Index: 145