Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4752 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5945. Min Act: -0.0001

Data Index: 254942 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5887. Min Act: -0.0001

Data Index: 1157532 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5746. Min Act: -0.0001

Data Index: 858213 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5643. Min Act: -0.0001

Data Index: 298597 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5636. Min Act: -0.0001

Data Index: 23503 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5538. Min Act: -0.0001

Data Index: 474196 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5628. Min Act: -0.0001

Data Index: 833847 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5452. Min Act: -0.0001

Data Index: 576204 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5512. Min Act: -0.0001

Data Index: 710054 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5433. Min Act: -0.0001

Data Index: 1357809 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5385. Min Act: -0.0001

Data Index: 46636 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5387. Min Act: -0.0001

Data Index: 186997 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5453. Min Act: -0.0001

Data Index: 724600 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5372. Min Act: -0.0001

Data Index: 263783 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5527. Min Act: -0.0001

Data Index: 649200 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5374. Min Act: -0.0001

Data Index: 50669 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5524. Min Act: -0.0001

Data Index: 780157 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5390. Min Act: -0.0001

Data Index: 1091605 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5401. Min Act: -0.0001

Data Index: 799264 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5347. Min Act: -0.0001

Data Index: 49326 (C4 (Web Text))

Max Activating Token Index: 166