Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1027 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.5529. Min Act: -0.0001

Data Index: 619925 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.4313. Min Act: -0.0001

Data Index: 300806 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.4528. Min Act: -0.0001

Data Index: 380256 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3977. Min Act: -0.0001

Data Index: 164530 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3445. Min Act: -0.0001

Data Index: 105106 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3077. Min Act: -0.0001

Data Index: 43657 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3240. Min Act: -0.0001

Data Index: 758302 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3505. Min Act: -0.0001

Data Index: 389810 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.2631. Min Act: -0.0001

Data Index: 1087410 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3391. Min Act: -0.0001

Data Index: 182811 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3906. Min Act: -0.0001

Data Index: 1308552 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3101. Min Act: -0.0001

Data Index: 1280764 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3562. Min Act: -0.0001

Data Index: 32038 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3049. Min Act: -0.0001

Data Index: 336276 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3364. Min Act: -0.0001

Data Index: 1291484 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3126. Min Act: -0.0001

Data Index: 683287 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.2176. Min Act: -0.0001

Data Index: 270626 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.2146. Min Act: -0.0001

Data Index: 509354 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.1806. Min Act: -0.0001

Data Index: 889055 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.2802. Min Act: -0.0001

Data Index: 270402 (C4 (Web Text))

Max Activating Token Index: 519