Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2376 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.4059. Min Act: -0.0004

Data Index: 619547 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.4063. Min Act: -0.0004

Data Index: 122486 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3763. Min Act: -0.0004

Data Index: 260323 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3753. Min Act: -0.0004

Data Index: 1009288 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3956. Min Act: -0.0004

Data Index: 264665 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3954. Min Act: -0.0004

Data Index: 718036 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3823. Min Act: -0.0004

Data Index: 588598 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.4086. Min Act: -0.0004

Data Index: 788778 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3795. Min Act: -0.0004

Data Index: 1242058 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3646. Min Act: -0.0004

Data Index: 994744 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3895. Min Act: -0.0004

Data Index: 1274881 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3636. Min Act: -0.0004

Data Index: 1067728 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3612. Min Act: -0.0004

Data Index: 1153022 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3739. Min Act: -0.0004

Data Index: 127715 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3767. Min Act: -0.0004

Data Index: 1013177 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.4163. Min Act: -0.0004

Data Index: 717424 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3870. Min Act: -0.0004

Data Index: 963064 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3728. Min Act: -0.0004

Data Index: 1170605 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3700. Min Act: -0.0004

Data Index: 645874 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3847. Min Act: -0.0004

Data Index: 1141126 (C4 (Web Text))

Max Activating Token Index: 710