Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3819 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.4039. Min Act: -0.0000

Data Index: 64163 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3503. Min Act: -0.0000

Data Index: 1074792 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3132. Min Act: -0.0000

Data Index: 635657 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3061. Min Act: -0.0000

Data Index: 878716 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3245. Min Act: -0.0000

Data Index: 428199 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3312. Min Act: -0.0000

Data Index: 1182072 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3302. Min Act: -0.0000

Data Index: 815773 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1330044 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3002. Min Act: -0.0000

Data Index: 632529 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.2916. Min Act: -0.0000

Data Index: 971370 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.2765. Min Act: -0.0000

Data Index: 991184 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.2899. Min Act: -0.0000

Data Index: 783705 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.2909. Min Act: -0.0000

Data Index: 1127805 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.2790. Min Act: -0.0000

Data Index: 1207829 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.2893. Min Act: -0.0000

Data Index: 840050 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.2855. Min Act: -0.0000

Data Index: 896096 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.2775. Min Act: -0.0000

Data Index: 473841 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1173456 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.2715. Min Act: -0.0000

Data Index: 501112 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.2747. Min Act: -0.0000

Data Index: 167013 (C4 (Web Text))

Max Activating Token Index: 532