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

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

Neuron 5617 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: 1.4949. Min Range: -1.4949

Max Act: 1.4949. Min Act: -0.0002

Data Index: 1325116 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.4533. Min Act: -0.0002

Data Index: 510291 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.3636. Min Act: -0.0002

Data Index: 1079291 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.3391. Min Act: -0.0002

Data Index: 993287 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.3611. Min Act: -0.0003

Data Index: 438827 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.3435. Min Act: -0.0002

Data Index: 1192207 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.3703. Min Act: -0.0002

Data Index: 923847 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.3652. Min Act: -0.0003

Data Index: 262814 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.3043. Min Act: -0.0002

Data Index: 430786 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.3103. Min Act: -0.0002

Data Index: 824182 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.3175. Min Act: -0.0002

Data Index: 780223 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.2900. Min Act: -0.0002

Data Index: 644030 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.2698. Min Act: -0.0002

Data Index: 963743 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.2906. Min Act: -0.0002

Data Index: 997246 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.2988. Min Act: -0.0002

Data Index: 1020961 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.2637. Min Act: -0.0002

Data Index: 779306 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.2658. Min Act: -0.0002

Data Index: 693323 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.3023. Min Act: -0.0002

Data Index: 931541 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.2880. Min Act: -0.0002

Data Index: 1063155 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 1.4949. Min Range: -1.4949

Max Act: 1.2628. Min Act: -0.0002

Data Index: 446380 (C4 (Web Text))

Max Activating Token Index: 940