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

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

Neuron 5977 in Layer 1

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: 1.2602. Min Range: -1.2602

Max Act: 1.2602. Min Act: -0.0002

Data Index: 871966 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.1564. Min Act: -0.0002

Data Index: 1105478 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.1564. Min Act: -0.0002

Data Index: 802052 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.1277. Min Act: -0.0002

Data Index: 948004 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.1291. Min Act: -0.0002

Data Index: 1313411 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.1124. Min Act: -0.0002

Data Index: 636174 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.0924. Min Act: -0.0002

Data Index: 276358 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.1201. Min Act: -0.0002

Data Index: 252604 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.0809. Min Act: -0.0002

Data Index: 149859 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.1002. Min Act: -0.0002

Data Index: 569125 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.1035. Min Act: -0.0002

Data Index: 1256034 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.0972. Min Act: -0.0002

Data Index: 360981 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.1174. Min Act: -0.0002

Data Index: 1181292 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.0744. Min Act: -0.0002

Data Index: 945193 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.0951. Min Act: -0.0002

Data Index: 1334807 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.0664. Min Act: -0.0002

Data Index: 819181 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.0846. Min Act: -0.0002

Data Index: 911710 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.1017. Min Act: -0.0002

Data Index: 675739 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.0639. Min Act: -0.0002

Data Index: 2033 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 1.2602. Min Range: -1.2602

Max Act: 1.0737. Min Act: -0.0002

Data Index: 369502 (C4 (Web Text))

Max Activating Token Index: 236