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

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

Neuron 542 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.5099. Min Act: -0.0002

Data Index: 989217 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4320. Min Act: -0.0002

Data Index: 590241 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4279. Min Act: -0.0002

Data Index: 680796 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4386. Min Act: -0.0002

Data Index: 1342051 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3882. Min Act: -0.0002

Data Index: 565753 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3942. Min Act: -0.0002

Data Index: 1039596 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3643. Min Act: -0.0002

Data Index: 8693 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3617. Min Act: -0.0002

Data Index: 396280 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3861. Min Act: -0.0002

Data Index: 1150026 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3605. Min Act: -0.0002

Data Index: 191916 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3711. Min Act: -0.0002

Data Index: 143874 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3830. Min Act: -0.0002

Data Index: 1222541 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3368. Min Act: -0.0002

Data Index: 1288248 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3691. Min Act: -0.0002

Data Index: 11794 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3312. Min Act: -0.0002

Data Index: 550905 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3461. Min Act: -0.0002

Data Index: 1276094 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3443. Min Act: -0.0002

Data Index: 1149365 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3513. Min Act: -0.0002

Data Index: 580932 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3369. Min Act: -0.0002

Data Index: 878188 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3265. Min Act: -0.0002

Data Index: 836334 (C4 (Web Text))

Max Activating Token Index: 380