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

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

Neuron 1827 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: 3.9529. Min Range: -3.9529

Max Act: 3.9358. Min Act: -0.1700

Data Index: 1215401 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 3.9529. Min Range: -3.9529

Max Act: 3.9529. Min Act: -0.1700

Data Index: 672201 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 3.9529. Min Range: -3.9529

Max Act: 3.9348. Min Act: -0.1700

Data Index: 23775 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 3.9529. Min Range: -3.9529

Max Act: 3.8956. Min Act: -0.1700

Data Index: 1015769 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 3.9529. Min Range: -3.9529

Max Act: 3.9006. Min Act: -0.1700

Data Index: 464402 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 3.9529. Min Range: -3.9529

Max Act: 3.8991. Min Act: -0.1700

Data Index: 1149904 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 3.9529. Min Range: -3.9529

Max Act: 3.8952. Min Act: -0.1700

Data Index: 179474 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 3.9529. Min Range: -3.9529

Max Act: 3.8665. Min Act: -0.1700

Data Index: 590739 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 3.9529. Min Range: -3.9529

Max Act: 3.8338. Min Act: -0.1700

Data Index: 1033197 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 3.9529. Min Range: -3.9529

Max Act: 3.8432. Min Act: -0.1700

Data Index: 317449 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 3.9529. Min Range: -3.9529

Max Act: 3.8251. Min Act: -0.1700

Data Index: 555507 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 3.9529. Min Range: -3.9529

Max Act: 3.7985. Min Act: -0.1700

Data Index: 913477 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 3.9529. Min Range: -3.9529

Max Act: 3.8249. Min Act: -0.1700

Data Index: 550610 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 3.9529. Min Range: -3.9529

Max Act: 3.8337. Min Act: -0.1700

Data Index: 1272234 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 3.9529. Min Range: -3.9529

Max Act: 3.8099. Min Act: -0.1700

Data Index: 1324371 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 3.9529. Min Range: -3.9529

Max Act: 3.7944. Min Act: -0.1700

Data Index: 246119 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 3.9529. Min Range: -3.9529

Max Act: 3.8206. Min Act: -0.1700

Data Index: 740795 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 3.9529. Min Range: -3.9529

Max Act: 3.8013. Min Act: -0.1700

Data Index: 609969 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 3.9529. Min Range: -3.9529

Max Act: 3.8069. Min Act: -0.1700

Data Index: 577019 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 3.9529. Min Range: -3.9529

Max Act: 3.7900. Min Act: -0.1700

Data Index: 425838 (C4 (Web Text))

Max Activating Token Index: 801