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

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

Neuron 266 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: 3.6242. Min Range: -3.6242

Max Act: 3.6242. Min Act: -0.1700

Data Index: 899881 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 3.6242. Min Range: -3.6242

Max Act: 3.5646. Min Act: -0.1700

Data Index: 453805 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 3.6242. Min Range: -3.6242

Max Act: 3.5685. Min Act: -0.1700

Data Index: 463844 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 3.6242. Min Range: -3.6242

Max Act: 3.5095. Min Act: -0.1700

Data Index: 82311 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 3.6242. Min Range: -3.6242

Max Act: 3.4632. Min Act: -0.1700

Data Index: 153357 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 3.6242. Min Range: -3.6242

Max Act: 3.4322. Min Act: -0.1700

Data Index: 1645784 (Python Code)

Max Activating Token Index: 873

Text #6

Max Range: 3.6242. Min Range: -3.6242

Max Act: 3.4359. Min Act: -0.1700

Data Index: 105909 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 3.6242. Min Range: -3.6242

Max Act: 3.4244. Min Act: -0.1700

Data Index: 111100 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 3.6242. Min Range: -3.6242

Max Act: 3.4264. Min Act: -0.1700

Data Index: 538230 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 3.6242. Min Range: -3.6242

Max Act: 3.4175. Min Act: -0.1700

Data Index: 1236512 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 3.6242. Min Range: -3.6242

Max Act: 3.4043. Min Act: -0.1700

Data Index: 1336226 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 3.6242. Min Range: -3.6242

Max Act: 3.3886. Min Act: -0.1700

Data Index: 93762 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 3.6242. Min Range: -3.6242

Max Act: 3.3910. Min Act: -0.1700

Data Index: 151716 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 3.6242. Min Range: -3.6242

Max Act: 3.3935. Min Act: -0.1700

Data Index: 426967 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 3.6242. Min Range: -3.6242

Max Act: 3.4125. Min Act: -0.1700

Data Index: 68487 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 3.6242. Min Range: -3.6242

Max Act: 3.4080. Min Act: -0.1700

Data Index: 1138270 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 3.6242. Min Range: -3.6242

Max Act: 3.4035. Min Act: -0.1700

Data Index: 583036 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 3.6242. Min Range: -3.6242

Max Act: 3.3878. Min Act: -0.1700

Data Index: 534780 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 3.6242. Min Range: -3.6242

Max Act: 3.4227. Min Act: -0.1700

Data Index: 186196 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 3.6242. Min Range: -3.6242

Max Act: 3.3786. Min Act: -0.1700

Data Index: 981497 (C4 (Web Text))

Max Activating Token Index: 27