Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1987 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.0795. Min Range: -5.0795

Max Act: 5.0483. Min Act: -0.1700

Data Index: 790198 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 5.0795. Min Range: -5.0795

Max Act: 5.0795. Min Act: -0.1698

Data Index: 131193 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 5.0795. Min Range: -5.0795

Max Act: 5.0170. Min Act: -0.1700

Data Index: 143082 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 5.0795. Min Range: -5.0795

Max Act: 4.9858. Min Act: -0.1700

Data Index: 423144 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 5.0795. Min Range: -5.0795

Max Act: 4.9858. Min Act: -0.1700

Data Index: 222693 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 5.0795. Min Range: -5.0795

Max Act: 4.8295. Min Act: -0.1700

Data Index: 560102 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 5.0795. Min Range: -5.0795

Max Act: 4.8608. Min Act: -0.1685

Data Index: 572439 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 5.0795. Min Range: -5.0795

Max Act: 4.8295. Min Act: -0.1700

Data Index: 1339029 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 5.0795. Min Range: -5.0795

Max Act: 4.7983. Min Act: -0.1700

Data Index: 299532 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 5.0795. Min Range: -5.0795

Max Act: 4.8295. Min Act: -0.1699

Data Index: 337390 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 5.0795. Min Range: -5.0795

Max Act: 4.7983. Min Act: -0.1700

Data Index: 526530 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 5.0795. Min Range: -5.0795

Max Act: 4.7670. Min Act: -0.1700

Data Index: 672037 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 5.0795. Min Range: -5.0795

Max Act: 4.7358. Min Act: -0.1700

Data Index: 269923 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 5.0795. Min Range: -5.0795

Max Act: 4.7670. Min Act: -0.1700

Data Index: 315937 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 5.0795. Min Range: -5.0795

Max Act: 4.7670. Min Act: -0.1700

Data Index: 611315 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 5.0795. Min Range: -5.0795

Max Act: 4.7045. Min Act: -0.1700

Data Index: 1202927 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 5.0795. Min Range: -5.0795

Max Act: 4.6420. Min Act: -0.1700

Data Index: 1161031 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 5.0795. Min Range: -5.0795

Max Act: 4.7045. Min Act: -0.1700

Data Index: 111965 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 5.0795. Min Range: -5.0795

Max Act: 4.7358. Min Act: -0.1700

Data Index: 480482 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 5.0795. Min Range: -5.0795

Max Act: 4.7358. Min Act: -0.1649

Data Index: 44638 (C4 (Web Text))

Max Activating Token Index: 121