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

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

Neuron 1569 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: 3.7385. Min Range: -3.7385

Max Act: 3.7385. Min Act: -0.1700

Data Index: 86082 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 3.7385. Min Range: -3.7385

Max Act: 3.7038. Min Act: -0.1438

Data Index: 725701 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 3.7385. Min Range: -3.7385

Max Act: 3.6562. Min Act: -0.1699

Data Index: 594736 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 3.7385. Min Range: -3.7385

Max Act: 3.6708. Min Act: -0.1699

Data Index: 947223 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 3.7385. Min Range: -3.7385

Max Act: 3.6086. Min Act: -0.1700

Data Index: 970318 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 3.7385. Min Range: -3.7385

Max Act: 3.5738. Min Act: -0.1700

Data Index: 1384525 (Python Code)

Max Activating Token Index: 196

Text #6

Max Range: 3.7385. Min Range: -3.7385

Max Act: 3.5369. Min Act: -0.1700

Data Index: 1158977 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 3.7385. Min Range: -3.7385

Max Act: 3.5332. Min Act: -0.1700

Data Index: 388203 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 3.7385. Min Range: -3.7385

Max Act: 3.5183. Min Act: -0.1699

Data Index: 830203 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 3.7385. Min Range: -3.7385

Max Act: 3.5099. Min Act: -0.1700

Data Index: 536171 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 3.7385. Min Range: -3.7385

Max Act: 3.5412. Min Act: -0.1700

Data Index: 1581939 (Python Code)

Max Activating Token Index: 501

Text #11

Max Range: 3.7385. Min Range: -3.7385

Max Act: 3.5121. Min Act: -0.1700

Data Index: 1408496 (Python Code)

Max Activating Token Index: 306

Text #12

Max Range: 3.7385. Min Range: -3.7385

Max Act: 3.5167. Min Act: -0.1700

Data Index: 1338566 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 3.7385. Min Range: -3.7385

Max Act: 3.4938. Min Act: -0.1700

Data Index: 1512036 (Python Code)

Max Activating Token Index: 874

Text #14

Max Range: 3.7385. Min Range: -3.7385

Max Act: 3.5107. Min Act: -0.1700

Data Index: 1088104 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 3.7385. Min Range: -3.7385

Max Act: 3.4931. Min Act: -0.1700

Data Index: 677238 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 3.7385. Min Range: -3.7385

Max Act: 3.5134. Min Act: -0.1699

Data Index: 848815 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 3.7385. Min Range: -3.7385

Max Act: 3.5057. Min Act: -0.1700

Data Index: 550486 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 3.7385. Min Range: -3.7385

Max Act: 3.5105. Min Act: -0.1700

Data Index: 1249586 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 3.7385. Min Range: -3.7385

Max Act: 3.4930. Min Act: -0.1700

Data Index: 324157 (C4 (Web Text))

Max Activating Token Index: 802