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

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

Neuron 907 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: 5.1163. Min Range: -5.1163

Max Act: 5.1163. Min Act: -0.1700

Data Index: 1201248 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 5.1163. Min Range: -5.1163

Max Act: 5.0225. Min Act: -0.1700

Data Index: 518065 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 5.1163. Min Range: -5.1163

Max Act: 5.0225. Min Act: -0.1700

Data Index: 415203 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 5.1163. Min Range: -5.1163

Max Act: 4.9913. Min Act: -0.1700

Data Index: 1141882 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 5.1163. Min Range: -5.1163

Max Act: 4.9600. Min Act: -0.1700

Data Index: 821407 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 5.1163. Min Range: -5.1163

Max Act: 5.0225. Min Act: -0.1700

Data Index: 341192 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 5.1163. Min Range: -5.1163

Max Act: 4.9600. Min Act: -0.1700

Data Index: 109466 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 5.1163. Min Range: -5.1163

Max Act: 4.9913. Min Act: -0.1700

Data Index: 272654 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 5.1163. Min Range: -5.1163

Max Act: 4.9913. Min Act: -0.1700

Data Index: 317670 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 5.1163. Min Range: -5.1163

Max Act: 4.9600. Min Act: -0.1700

Data Index: 1204006 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 5.1163. Min Range: -5.1163

Max Act: 4.9288. Min Act: -0.1700

Data Index: 830116 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 5.1163. Min Range: -5.1163

Max Act: 4.9913. Min Act: -0.1700

Data Index: 34061 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 5.1163. Min Range: -5.1163

Max Act: 4.9600. Min Act: -0.1700

Data Index: 542324 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 5.1163. Min Range: -5.1163

Max Act: 4.8975. Min Act: -0.1700

Data Index: 1070950 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 5.1163. Min Range: -5.1163

Max Act: 4.9600. Min Act: -0.1700

Data Index: 534180 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 5.1163. Min Range: -5.1163

Max Act: 4.9288. Min Act: -0.1700

Data Index: 1219873 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 5.1163. Min Range: -5.1163

Max Act: 4.9288. Min Act: -0.1700

Data Index: 1302205 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 5.1163. Min Range: -5.1163

Max Act: 4.9288. Min Act: -0.1700

Data Index: 58733 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 5.1163. Min Range: -5.1163

Max Act: 4.8975. Min Act: -0.1700

Data Index: 170280 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 5.1163. Min Range: -5.1163

Max Act: 4.8975. Min Act: -0.1700

Data Index: 77201 (C4 (Web Text))

Max Activating Token Index: 331