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

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

Neuron 76 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2944. Min Act: -0.0001

Data Index: 1633916 (Python Code)

Max Activating Token Index: 669

Text #1

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2897. Min Act: -0.0001

Data Index: 1421622 (Python Code)

Max Activating Token Index: 817

Text #2

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2767. Min Act: -0.0001

Data Index: 1398027 (Python Code)

Max Activating Token Index: 903

Text #3

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2551. Min Act: -0.0001

Data Index: 1440582 (Python Code)

Max Activating Token Index: 938

Text #4

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2401. Min Act: -0.0001

Data Index: 1555723 (Python Code)

Max Activating Token Index: 786

Text #5

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2620. Min Act: -0.0001

Data Index: 1395499 (Python Code)

Max Activating Token Index: 862

Text #6

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2365. Min Act: -0.0001

Data Index: 136575 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2347. Min Act: -0.0001

Data Index: 1535414 (Python Code)

Max Activating Token Index: 285

Text #8

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2057. Min Act: -0.0001

Data Index: 1473751 (Python Code)

Max Activating Token Index: 759

Text #9

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2026. Min Act: -0.0001

Data Index: 1431837 (Python Code)

Max Activating Token Index: 623

Text #10

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2106. Min Act: -0.0001

Data Index: 1423491 (Python Code)

Max Activating Token Index: 984

Text #11

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.1939. Min Act: -0.0001

Data Index: 1520630 (Python Code)

Max Activating Token Index: 1009

Text #12

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2077. Min Act: -0.0001

Data Index: 1482031 (Python Code)

Max Activating Token Index: 486

Text #13

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.1923. Min Act: -0.0001

Data Index: 1550594 (Python Code)

Max Activating Token Index: 66

Text #14

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2051. Min Act: -0.0001

Data Index: 1445026 (Python Code)

Max Activating Token Index: 457

Text #15

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.1919. Min Act: -0.0001

Data Index: 1397685 (Python Code)

Max Activating Token Index: 163

Text #16

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.1865. Min Act: -0.0001

Data Index: 1430151 (Python Code)

Max Activating Token Index: 659

Text #17

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.1983. Min Act: -0.0001

Data Index: 1655626 (Python Code)

Max Activating Token Index: 221

Text #18

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.1901. Min Act: -0.0001

Data Index: 1527307 (Python Code)

Max Activating Token Index: 374

Text #19

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.1886. Min Act: -0.0001

Data Index: 1367387 (Python Code)

Max Activating Token Index: 669