Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1529 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.6665. Min Act: -0.1700

Data Index: 689065 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.6352. Min Act: -0.1700

Data Index: 1171074 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.6040. Min Act: -0.1700

Data Index: 965163 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.4165. Min Act: -0.1700

Data Index: 236518 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.4790. Min Act: -0.1700

Data Index: 1273933 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.4165. Min Act: -0.1700

Data Index: 35071 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.4790. Min Act: -0.1700

Data Index: 229755 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.4165. Min Act: -0.1700

Data Index: 1309092 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.3852. Min Act: -0.1700

Data Index: 782097 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.4165. Min Act: -0.1700

Data Index: 369717 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.4165. Min Act: -0.1700

Data Index: 455185 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.3852. Min Act: -0.1700

Data Index: 342920 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.4165. Min Act: -0.1700

Data Index: 564686 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.3852. Min Act: -0.1700

Data Index: 703621 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.3540. Min Act: -0.1700

Data Index: 980915 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.3540. Min Act: -0.1700

Data Index: 45982 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.3227. Min Act: -0.1700

Data Index: 717828 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.3540. Min Act: -0.1700

Data Index: 4172 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.3852. Min Act: -0.1700

Data Index: 822924 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 5.6665. Min Range: -5.6665

Max Act: 5.3540. Min Act: -0.1700

Data Index: 915765 (C4 (Web Text))

Max Activating Token Index: 343