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

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

Neuron 1183 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: 4.4291. Min Range: -4.4291

Max Act: 4.4291. Min Act: -0.1700

Data Index: 1159310 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.4008. Min Act: -0.1700

Data Index: 204113 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.3983. Min Act: -0.1700

Data Index: 528902 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.3215. Min Act: -0.1700

Data Index: 1298585 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.3278. Min Act: -0.1700

Data Index: 863482 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.3097. Min Act: -0.1700

Data Index: 46436 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2918. Min Act: -0.1700

Data Index: 781523 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2933. Min Act: -0.1700

Data Index: 1155584 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2713. Min Act: -0.1700

Data Index: 1341798 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2839. Min Act: -0.1700

Data Index: 39051 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.3004. Min Act: -0.1700

Data Index: 1210180 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2753. Min Act: -0.1700

Data Index: 1022301 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2853. Min Act: -0.1700

Data Index: 309903 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2372. Min Act: -0.1700

Data Index: 1600246 (Python Code)

Max Activating Token Index: 667

Text #14

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2047. Min Act: -0.1700

Data Index: 1197802 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2218. Min Act: -0.1700

Data Index: 976582 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2060. Min Act: -0.1700

Data Index: 1279098 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2165. Min Act: -0.1700

Data Index: 1289908 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2003. Min Act: -0.1700

Data Index: 313363 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2028. Min Act: -0.1700

Data Index: 1178078 (C4 (Web Text))

Max Activating Token Index: 73