Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 690 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.4041. Min Range: -5.4041

Max Act: 5.4041. Min Act: -0.1700

Data Index: 820793 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 5.4041. Min Range: -5.4041

Max Act: 5.2791. Min Act: -0.1700

Data Index: 1197036 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 5.4041. Min Range: -5.4041

Max Act: 5.3103. Min Act: -0.1700

Data Index: 487922 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 5.4041. Min Range: -5.4041

Max Act: 5.0916. Min Act: -0.1700

Data Index: 687861 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 5.4041. Min Range: -5.4041

Max Act: 5.1853. Min Act: -0.1700

Data Index: 156834 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 5.4041. Min Range: -5.4041

Max Act: 5.0291. Min Act: -0.1700

Data Index: 562873 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 5.4041. Min Range: -5.4041

Max Act: 4.9978. Min Act: -0.1700

Data Index: 730457 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 5.4041. Min Range: -5.4041

Max Act: 5.1541. Min Act: -0.1700

Data Index: 1115133 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 5.4041. Min Range: -5.4041

Max Act: 5.1228. Min Act: -0.1700

Data Index: 530255 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 5.4041. Min Range: -5.4041

Max Act: 5.0291. Min Act: -0.1700

Data Index: 246064 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 5.4041. Min Range: -5.4041

Max Act: 5.0291. Min Act: -0.1700

Data Index: 703940 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 5.4041. Min Range: -5.4041

Max Act: 4.9978. Min Act: -0.1700

Data Index: 1076942 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 5.4041. Min Range: -5.4041

Max Act: 4.9666. Min Act: -0.1700

Data Index: 986719 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 5.4041. Min Range: -5.4041

Max Act: 4.8728. Min Act: -0.1700

Data Index: 1184169 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 5.4041. Min Range: -5.4041

Max Act: 4.9666. Min Act: -0.1700

Data Index: 927184 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 5.4041. Min Range: -5.4041

Max Act: 4.9353. Min Act: -0.1700

Data Index: 668021 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 5.4041. Min Range: -5.4041

Max Act: 4.9666. Min Act: -0.1700

Data Index: 1083270 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 5.4041. Min Range: -5.4041

Max Act: 4.9353. Min Act: -0.1700

Data Index: 1113564 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 5.4041. Min Range: -5.4041

Max Act: 4.9353. Min Act: -0.1700

Data Index: 450820 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 5.4041. Min Range: -5.4041

Max Act: 4.8416. Min Act: -0.1700

Data Index: 66558 (C4 (Web Text))

Max Activating Token Index: 284