Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1991 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.5620. Min Range: -5.5620

Max Act: 5.5620. Min Act: -0.1700

Data Index: 636095 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 5.5620. Min Range: -5.5620

Max Act: 5.2808. Min Act: -0.1700

Data Index: 664440 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 5.5620. Min Range: -5.5620

Max Act: 5.2183. Min Act: -0.1700

Data Index: 1164390 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 5.5620. Min Range: -5.5620

Max Act: 5.2495. Min Act: -0.1700

Data Index: 1238745 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 5.5620. Min Range: -5.5620

Max Act: 5.2183. Min Act: -0.1700

Data Index: 1306319 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 5.5620. Min Range: -5.5620

Max Act: 5.1870. Min Act: -0.1700

Data Index: 1249351 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 5.5620. Min Range: -5.5620

Max Act: 5.0933. Min Act: -0.1700

Data Index: 297228 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 5.5620. Min Range: -5.5620

Max Act: 5.1245. Min Act: -0.1700

Data Index: 1354299 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 5.5620. Min Range: -5.5620

Max Act: 5.0933. Min Act: -0.1700

Data Index: 939812 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 5.5620. Min Range: -5.5620

Max Act: 5.0933. Min Act: -0.1700

Data Index: 1078343 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 5.5620. Min Range: -5.5620

Max Act: 5.0933. Min Act: -0.1700

Data Index: 312291 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 5.5620. Min Range: -5.5620

Max Act: 5.0308. Min Act: -0.1700

Data Index: 494610 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 5.5620. Min Range: -5.5620

Max Act: 5.0308. Min Act: -0.1700

Data Index: 853622 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 5.5620. Min Range: -5.5620

Max Act: 5.0620. Min Act: -0.1700

Data Index: 1350886 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 5.5620. Min Range: -5.5620

Max Act: 5.0620. Min Act: -0.1700

Data Index: 687837 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 5.5620. Min Range: -5.5620

Max Act: 5.0308. Min Act: -0.1700

Data Index: 408950 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 5.5620. Min Range: -5.5620

Max Act: 4.9995. Min Act: -0.1700

Data Index: 988671 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 5.5620. Min Range: -5.5620

Max Act: 5.0308. Min Act: -0.1700

Data Index: 1062259 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 5.5620. Min Range: -5.5620

Max Act: 5.0308. Min Act: -0.1700

Data Index: 1031967 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 5.5620. Min Range: -5.5620

Max Act: 4.9995. Min Act: -0.1700

Data Index: 764482 (C4 (Web Text))

Max Activating Token Index: 153