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

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

Neuron 396 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: 3.7916. Min Range: -3.7916

Max Act: 3.7803. Min Act: -0.1700

Data Index: 145607 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 3.7916. Min Range: -3.7916

Max Act: 3.7649. Min Act: -0.1700

Data Index: 875693 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 3.7916. Min Range: -3.7916

Max Act: 3.7916. Min Act: -0.1700

Data Index: 200899 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 3.7916. Min Range: -3.7916

Max Act: 3.7663. Min Act: -0.1700

Data Index: 1184466 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 3.7916. Min Range: -3.7916

Max Act: 3.7540. Min Act: -0.1700

Data Index: 994373 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 3.7916. Min Range: -3.7916

Max Act: 3.7270. Min Act: -0.1699

Data Index: 1040788 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 3.7916. Min Range: -3.7916

Max Act: 3.7319. Min Act: -0.1700

Data Index: 926892 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 3.7916. Min Range: -3.7916

Max Act: 3.7108. Min Act: -0.1700

Data Index: 43544 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 3.7916. Min Range: -3.7916

Max Act: 3.7235. Min Act: -0.1700

Data Index: 87977 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 3.7916. Min Range: -3.7916

Max Act: 3.6941. Min Act: -0.1700

Data Index: 305996 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 3.7916. Min Range: -3.7916

Max Act: 3.7269. Min Act: -0.1700

Data Index: 69356 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 3.7916. Min Range: -3.7916

Max Act: 3.6932. Min Act: -0.1700

Data Index: 96479 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 3.7916. Min Range: -3.7916

Max Act: 3.6838. Min Act: -0.1700

Data Index: 1289044 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 3.7916. Min Range: -3.7916

Max Act: 3.7042. Min Act: -0.1700

Data Index: 213676 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 3.7916. Min Range: -3.7916

Max Act: 3.6908. Min Act: -0.1700

Data Index: 212465 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 3.7916. Min Range: -3.7916

Max Act: 3.6841. Min Act: -0.1700

Data Index: 165048 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 3.7916. Min Range: -3.7916

Max Act: 3.6654. Min Act: -0.1700

Data Index: 156561 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 3.7916. Min Range: -3.7916

Max Act: 3.6764. Min Act: -0.1700

Data Index: 398085 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 3.7916. Min Range: -3.7916

Max Act: 3.6764. Min Act: -0.1700

Data Index: 101049 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 3.7916. Min Range: -3.7916

Max Act: 3.6990. Min Act: -0.1700

Data Index: 473933 (C4 (Web Text))

Max Activating Token Index: 665