Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2535 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.5535. Min Act: -0.0001

Data Index: 4320 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.5348. Min Act: -0.0001

Data Index: 589741 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.5206. Min Act: -0.0001

Data Index: 725566 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.5201. Min Act: -0.0001

Data Index: 671623 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.5052. Min Act: -0.0001

Data Index: 1217982 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.5099. Min Act: -0.0001

Data Index: 224314 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.5015. Min Act: -0.0001

Data Index: 438467 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.5220. Min Act: -0.0001

Data Index: 1078228 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4933. Min Act: -0.0001

Data Index: 343121 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4745. Min Act: -0.0001

Data Index: 195767 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4890. Min Act: -0.0001

Data Index: 271996 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4868. Min Act: -0.0001

Data Index: 292530 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4657. Min Act: -0.0001

Data Index: 477218 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4544. Min Act: -0.0001

Data Index: 1037006 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4936. Min Act: -0.0001

Data Index: 1225140 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4598. Min Act: -0.0001

Data Index: 371408 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4945. Min Act: -0.0001

Data Index: 1026545 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4687. Min Act: -0.0001

Data Index: 426052 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4386. Min Act: -0.0001

Data Index: 1073300 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4870. Min Act: -0.0001

Data Index: 224903 (C4 (Web Text))

Max Activating Token Index: 566