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

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

Neuron 1666 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: 5.2132. Min Range: -5.2132

Max Act: 5.2132. Min Act: -0.1700

Data Index: 449019 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.9320. Min Act: -0.1700

Data Index: 5488 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.8695. Min Act: -0.1700

Data Index: 33253 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.7757. Min Act: -0.1700

Data Index: 1051897 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.7445. Min Act: -0.1700

Data Index: 319407 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.8070. Min Act: -0.1700

Data Index: 568351 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.7445. Min Act: -0.1700

Data Index: 96909 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.7132. Min Act: -0.1700

Data Index: 357419 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.6507. Min Act: -0.1700

Data Index: 344084 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.6195. Min Act: -0.1700

Data Index: 1317931 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.6195. Min Act: -0.1700

Data Index: 1174524 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.6195. Min Act: -0.1700

Data Index: 893998 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.5882. Min Act: -0.1700

Data Index: 656001 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.6507. Min Act: -0.1700

Data Index: 252636 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.6195. Min Act: -0.1700

Data Index: 457859 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.5882. Min Act: -0.1700

Data Index: 816181 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.5882. Min Act: -0.1700

Data Index: 140952 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.5257. Min Act: -0.1700

Data Index: 1208368 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.5257. Min Act: -0.1700

Data Index: 486401 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.5570. Min Act: -0.1700

Data Index: 365722 (C4 (Web Text))

Max Activating Token Index: 253