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

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

Neuron 955 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: 4.5944. Min Range: -4.5944

Max Act: 4.5944. Min Act: -0.0000

Data Index: 990367 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 4.5944. Min Range: -4.5944

Max Act: 4.2195. Min Act: -0.0000

Data Index: 188905 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 4.5944. Min Range: -4.5944

Max Act: 4.2064. Min Act: -0.0000

Data Index: 1019221 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 4.5944. Min Range: -4.5944

Max Act: 3.9966. Min Act: -0.0000

Data Index: 1231203 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 4.5944. Min Range: -4.5944

Max Act: 3.9483. Min Act: -0.0000

Data Index: 490663 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 4.5944. Min Range: -4.5944

Max Act: 3.2030. Min Act: -0.0000

Data Index: 867826 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 4.5944. Min Range: -4.5944

Max Act: 3.8462. Min Act: -0.0000

Data Index: 589790 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 4.5944. Min Range: -4.5944

Max Act: 3.2796. Min Act: -0.0000

Data Index: 726066 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 4.5944. Min Range: -4.5944

Max Act: 3.5756. Min Act: -0.0000

Data Index: 1276816 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 4.5944. Min Range: -4.5944

Max Act: 3.3857. Min Act: -0.0000

Data Index: 849771 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 4.5944. Min Range: -4.5944

Max Act: 3.1081. Min Act: -0.0000

Data Index: 183441 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 4.5944. Min Range: -4.5944

Max Act: 3.0621. Min Act: -0.0000

Data Index: 1071818 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 4.5944. Min Range: -4.5944

Max Act: 3.0127. Min Act: -0.0000

Data Index: 975043 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 4.5944. Min Range: -4.5944

Max Act: 2.5585. Min Act: -0.0000

Data Index: 190488 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 4.5944. Min Range: -4.5944

Max Act: 3.2388. Min Act: -0.0000

Data Index: 278734 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 4.5944. Min Range: -4.5944

Max Act: 2.8163. Min Act: -0.0000

Data Index: 1220460 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 4.5944. Min Range: -4.5944

Max Act: 2.9097. Min Act: -0.0000

Data Index: 752552 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 4.5944. Min Range: -4.5944

Max Act: 2.6539. Min Act: -0.0000

Data Index: 955926 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 4.5944. Min Range: -4.5944

Max Act: 2.5338. Min Act: -0.0000

Data Index: 900059 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 4.5944. Min Range: -4.5944

Max Act: 2.8036. Min Act: -0.0000

Data Index: 792408 (C4 (Web Text))

Max Activating Token Index: 341