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

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

Neuron 780 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: 3.3277. Min Range: -3.3277

Max Act: 3.3277. Min Act: -0.1700

Data Index: 1228307 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 3.3277. Min Range: -3.3277

Max Act: 3.3174. Min Act: -0.1700

Data Index: 263774 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 3.3277. Min Range: -3.3277

Max Act: 3.2996. Min Act: -0.1700

Data Index: 63438 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 3.3277. Min Range: -3.3277

Max Act: 3.2798. Min Act: -0.1700

Data Index: 328020 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 3.3277. Min Range: -3.3277

Max Act: 3.2706. Min Act: -0.1700

Data Index: 1014058 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 3.3277. Min Range: -3.3277

Max Act: 3.2859. Min Act: -0.1700

Data Index: 850537 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 3.3277. Min Range: -3.3277

Max Act: 3.2403. Min Act: -0.1700

Data Index: 139973 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 3.3277. Min Range: -3.3277

Max Act: 3.2569. Min Act: -0.1700

Data Index: 403370 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 3.3277. Min Range: -3.3277

Max Act: 3.2310. Min Act: -0.1700

Data Index: 1184359 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 3.3277. Min Range: -3.3277

Max Act: 3.2037. Min Act: -0.1700

Data Index: 1328063 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 3.3277. Min Range: -3.3277

Max Act: 3.2300. Min Act: -0.1439

Data Index: 1142762 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 3.3277. Min Range: -3.3277

Max Act: 3.2237. Min Act: -0.1700

Data Index: 836359 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 3.3277. Min Range: -3.3277

Max Act: 3.1994. Min Act: -0.1700

Data Index: 1187503 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 3.3277. Min Range: -3.3277

Max Act: 3.2060. Min Act: -0.1615

Data Index: 1302608 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 3.3277. Min Range: -3.3277

Max Act: 3.2040. Min Act: -0.1700

Data Index: 965881 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 3.3277. Min Range: -3.3277

Max Act: 3.2102. Min Act: -0.1699

Data Index: 669662 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 3.3277. Min Range: -3.3277

Max Act: 3.1916. Min Act: -0.1700

Data Index: 364414 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 3.3277. Min Range: -3.3277

Max Act: 3.1735. Min Act: -0.1700

Data Index: 981542 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 3.3277. Min Range: -3.3277

Max Act: 3.1827. Min Act: -0.1700

Data Index: 263185 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 3.3277. Min Range: -3.3277

Max Act: 3.2002. Min Act: -0.1700

Data Index: 757163 (C4 (Web Text))

Max Activating Token Index: 554