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

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

Neuron 4416 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5864. Min Act: -0.0000

Data Index: 249138 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5393. Min Act: -0.0000

Data Index: 438124 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4824. Min Act: -0.0000

Data Index: 314678 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4672. Min Act: -0.0000

Data Index: 623752 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4549. Min Act: -0.0000

Data Index: 1357606 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4722. Min Act: -0.0000

Data Index: 384152 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4636. Min Act: -0.0000

Data Index: 650881 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4506. Min Act: -0.0000

Data Index: 1134778 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4513. Min Act: -0.0000

Data Index: 19946 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4387. Min Act: -0.0000

Data Index: 892223 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4388. Min Act: -0.0000

Data Index: 669414 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4286. Min Act: -0.0000

Data Index: 627849 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1285292 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4058. Min Act: -0.0000

Data Index: 613662 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4007. Min Act: -0.0000

Data Index: 149958 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4288. Min Act: -0.0000

Data Index: 272411 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4121. Min Act: -0.0000

Data Index: 1156430 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1025523 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4139. Min Act: -0.0000

Data Index: 60967 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4371. Min Act: -0.0000

Data Index: 527731 (C4 (Web Text))

Max Activating Token Index: 281