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

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

Neuron 1164 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: 3.3818. Min Range: -3.3818

Max Act: 3.3818. Min Act: -0.1700

Data Index: 1163036 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 3.3818. Min Range: -3.3818

Max Act: 3.3784. Min Act: -0.1700

Data Index: 173607 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 3.3818. Min Range: -3.3818

Max Act: 3.3451. Min Act: -0.1700

Data Index: 256510 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 3.3818. Min Range: -3.3818

Max Act: 3.3351. Min Act: -0.1700

Data Index: 651457 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 3.3818. Min Range: -3.3818

Max Act: 3.3221. Min Act: -0.1700

Data Index: 564044 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 3.3818. Min Range: -3.3818

Max Act: 3.2997. Min Act: -0.1700

Data Index: 334745 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 3.3818. Min Range: -3.3818

Max Act: 3.2701. Min Act: -0.1700

Data Index: 451055 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 3.3818. Min Range: -3.3818

Max Act: 3.2939. Min Act: -0.1700

Data Index: 540618 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 3.3818. Min Range: -3.3818

Max Act: 3.2766. Min Act: -0.1700

Data Index: 954445 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 3.3818. Min Range: -3.3818

Max Act: 3.2381. Min Act: -0.1700

Data Index: 496040 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 3.3818. Min Range: -3.3818

Max Act: 3.2393. Min Act: -0.1700

Data Index: 1113191 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 3.3818. Min Range: -3.3818

Max Act: 3.2456. Min Act: -0.1700

Data Index: 64227 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 3.3818. Min Range: -3.3818

Max Act: 3.2424. Min Act: -0.1700

Data Index: 1047559 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 3.3818. Min Range: -3.3818

Max Act: 3.2345. Min Act: -0.1700

Data Index: 963071 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 3.3818. Min Range: -3.3818

Max Act: 3.2188. Min Act: -0.1700

Data Index: 240876 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 3.3818. Min Range: -3.3818

Max Act: 3.2388. Min Act: -0.1700

Data Index: 1183673 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 3.3818. Min Range: -3.3818

Max Act: 3.2110. Min Act: -0.1700

Data Index: 136111 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 3.3818. Min Range: -3.3818

Max Act: 3.2295. Min Act: -0.1700

Data Index: 717844 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 3.3818. Min Range: -3.3818

Max Act: 3.2109. Min Act: -0.1700

Data Index: 205541 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 3.3818. Min Range: -3.3818

Max Act: 3.2003. Min Act: -0.1700

Data Index: 237114 (C4 (Web Text))

Max Activating Token Index: 66