Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4811 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.6512. Min Act: -0.0000

Data Index: 462985 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.6597. Min Act: -0.0000

Data Index: 276153 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.6337. Min Act: -0.0000

Data Index: 717174 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.3424. Min Act: -0.0000

Data Index: 444708 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.4156. Min Act: -0.0000

Data Index: 931295 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.2908. Min Act: -0.0000

Data Index: 872493 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.3018. Min Act: -0.0000

Data Index: 814278 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.2803. Min Act: -0.0000

Data Index: 1355207 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.2845. Min Act: -0.0000

Data Index: 1255507 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.1435. Min Act: -0.0000

Data Index: 96923 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.2763. Min Act: -0.0000

Data Index: 360503 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.2575. Min Act: -0.0000

Data Index: 1001350 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.1420. Min Act: -0.0000

Data Index: 97294 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.3233. Min Act: -0.0000

Data Index: 1044163 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.1908. Min Act: -0.0000

Data Index: 539474 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.1348. Min Act: -0.0000

Data Index: 1240129 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.1286. Min Act: -0.0000

Data Index: 382990 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.0036. Min Act: -0.0000

Data Index: 837695 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.0804. Min Act: -0.0000

Data Index: 708481 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.0815. Min Act: -0.0000

Data Index: 1273496 (C4 (Web Text))

Max Activating Token Index: 835