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

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

Neuron 1630 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6575. Min Act: -0.0000

Data Index: 310560 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.7648. Min Act: -0.0000

Data Index: 1266990 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.8133. Min Act: -0.0000

Data Index: 336161 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.7121. Min Act: -0.0000

Data Index: 1071808 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6978. Min Act: -0.0000

Data Index: 401236 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6690. Min Act: -0.0000

Data Index: 1168286 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.7097. Min Act: -0.0000

Data Index: 913506 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6115. Min Act: -0.0000

Data Index: 812270 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6292. Min Act: -0.0000

Data Index: 774460 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6406. Min Act: -0.0000

Data Index: 444769 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6725. Min Act: -0.0000

Data Index: 1281492 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6312. Min Act: -0.0000

Data Index: 1166706 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6049. Min Act: -0.0001

Data Index: 254584 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.7176. Min Act: -0.0001

Data Index: 221964 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6585. Min Act: -0.0000

Data Index: 924548 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6481. Min Act: -0.0000

Data Index: 1286214 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5923. Min Act: -0.0000

Data Index: 1164662 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5877. Min Act: -0.0000

Data Index: 1010616 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6261. Min Act: -0.0000

Data Index: 84415 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5440. Min Act: -0.0000

Data Index: 631651 (C4 (Web Text))

Max Activating Token Index: 721