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

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

Neuron 2320 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.3388. Min Act: -0.0001

Data Index: 660768 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.3074. Min Act: -0.0001

Data Index: 263191 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.3020. Min Act: -0.0001

Data Index: 662900 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2920. Min Act: -0.0001

Data Index: 797987 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2829. Min Act: -0.0001

Data Index: 237778 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2920. Min Act: -0.0001

Data Index: 1219600 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2886. Min Act: -0.0001

Data Index: 933387 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2798. Min Act: -0.0001

Data Index: 1263346 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2597. Min Act: -0.0001

Data Index: 1133601 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2505. Min Act: -0.0001

Data Index: 1157256 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2967. Min Act: -0.0001

Data Index: 985493 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2501. Min Act: -0.0001

Data Index: 125436 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2477. Min Act: -0.0001

Data Index: 950097 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2672. Min Act: -0.0000

Data Index: 727188 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1224833 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2555. Min Act: -0.0001

Data Index: 459366 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2518. Min Act: -0.0001

Data Index: 1231998 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2345. Min Act: -0.0001

Data Index: 677336 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2322. Min Act: -0.0001

Data Index: 1197920 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 0.3388. Min Range: -0.3388

Max Act: 0.2453. Min Act: -0.0001

Data Index: 163224 (C4 (Web Text))

Max Activating Token Index: 328