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

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

Neuron 1755 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6852. Min Range: -4.6852

Max Act: 4.6852. Min Act: -0.0000

Data Index: 54733 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 4.6852. Min Range: -4.6852

Max Act: 3.8554. Min Act: -0.0001

Data Index: 1655680 (Python Code)

Max Activating Token Index: 311

Text #2

Max Range: 4.6852. Min Range: -4.6852

Max Act: 3.7839. Min Act: -0.0000

Data Index: 330203 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 4.6852. Min Range: -4.6852

Max Act: 3.2424. Min Act: -0.0000

Data Index: 200096 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 4.6852. Min Range: -4.6852

Max Act: 3.2887. Min Act: -0.0001

Data Index: 604778 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 4.6852. Min Range: -4.6852

Max Act: 3.2782. Min Act: -0.0000

Data Index: 1306511 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 4.6852. Min Range: -4.6852

Max Act: 3.3271. Min Act: -0.0000

Data Index: 408478 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 4.6852. Min Range: -4.6852

Max Act: 3.3857. Min Act: -0.0001

Data Index: 956235 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 4.6852. Min Range: -4.6852

Max Act: 3.2538. Min Act: -0.0001

Data Index: 549661 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 4.6852. Min Range: -4.6852

Max Act: 3.3067. Min Act: -0.0000

Data Index: 268745 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 4.6852. Min Range: -4.6852

Max Act: 3.1956. Min Act: -0.0001

Data Index: 1317363 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 4.6852. Min Range: -4.6852

Max Act: 3.1457. Min Act: -0.0001

Data Index: 1156118 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 4.6852. Min Range: -4.6852

Max Act: 3.1017. Min Act: -0.0000

Data Index: 602014 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 4.6852. Min Range: -4.6852

Max Act: 3.0423. Min Act: -0.0001

Data Index: 166092 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 4.6852. Min Range: -4.6852

Max Act: 2.9338. Min Act: -0.0000

Data Index: 1042948 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 4.6852. Min Range: -4.6852

Max Act: 2.9099. Min Act: -0.0000

Data Index: 1341875 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 4.6852. Min Range: -4.6852

Max Act: 2.9451. Min Act: -0.0000

Data Index: 417904 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 4.6852. Min Range: -4.6852

Max Act: 2.9221. Min Act: -0.0001

Data Index: 854208 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 4.6852. Min Range: -4.6852

Max Act: 2.8755. Min Act: -0.0000

Data Index: 609556 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 4.6852. Min Range: -4.6852

Max Act: 2.9174. Min Act: -0.0001

Data Index: 898407 (C4 (Web Text))

Max Activating Token Index: 939