Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1768 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0518. Min Act: -0.0006

Data Index: 818068 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0507. Min Act: -0.0006

Data Index: 1086404 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0489. Min Act: -0.0006

Data Index: 754450 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0451. Min Act: -0.0006

Data Index: 1164240 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0469. Min Act: -0.0006

Data Index: 135412 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0460. Min Act: -0.0006

Data Index: 100993 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0462. Min Act: -0.0006

Data Index: 634824 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0455. Min Act: -0.0006

Data Index: 1322042 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0466. Min Act: -0.0006

Data Index: 1144300 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0444. Min Act: -0.0006

Data Index: 1587921 (Python Code)

Max Activating Token Index: 844

Text #10

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0449. Min Act: -0.0006

Data Index: 1317500 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0454. Min Act: -0.0006

Data Index: 154425 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0461. Min Act: -0.0006

Data Index: 977178 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0431. Min Act: -0.0006

Data Index: 1175028 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0450. Min Act: -0.0006

Data Index: 846605 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0421. Min Act: -0.0006

Data Index: 1065890 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0445. Min Act: -0.0006

Data Index: 626591 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0435. Min Act: -0.0006

Data Index: 409820 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0430. Min Act: -0.0006

Data Index: 401384 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0440. Min Act: -0.0006

Data Index: 411099 (C4 (Web Text))

Max Activating Token Index: 915