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

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

Neuron 1510 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: 4.6058. Min Range: -4.6058

Max Act: 4.6058. Min Act: -0.1700

Data Index: 117257 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.4595. Min Act: -0.1700

Data Index: 63307 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.4325. Min Act: -0.1700

Data Index: 807915 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.4490. Min Act: -0.1700

Data Index: 1340656 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.4366. Min Act: -0.1700

Data Index: 690829 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.4475. Min Act: -0.1700

Data Index: 443414 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.4383. Min Act: -0.1700

Data Index: 316634 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.4048. Min Act: -0.1700

Data Index: 442025 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.4106. Min Act: -0.1700

Data Index: 1045120 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.4066. Min Act: -0.1700

Data Index: 219820 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.4084. Min Act: -0.1700

Data Index: 1037259 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.4006. Min Act: -0.1700

Data Index: 1023793 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.3612. Min Act: -0.1700

Data Index: 1297555 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.3586. Min Act: -0.1700

Data Index: 881203 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.3773. Min Act: -0.1700

Data Index: 426669 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.3850. Min Act: -0.1700

Data Index: 1056916 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.2891. Min Act: -0.1700

Data Index: 287070 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.2967. Min Act: -0.1700

Data Index: 1014607 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.2992. Min Act: -0.1700

Data Index: 922042 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.3078. Min Act: -0.1700

Data Index: 995177 (C4 (Web Text))

Max Activating Token Index: 842