Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3208 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7249. Min Range: -2.7249

Max Act: 2.7249. Min Act: -0.0000

Data Index: 454584 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 2.7249. Min Range: -2.7249

Max Act: 2.6480. Min Act: -0.0000

Data Index: 1031534 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 2.7249. Min Range: -2.7249

Max Act: 2.4632. Min Act: -0.0000

Data Index: 706837 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 2.7249. Min Range: -2.7249

Max Act: 2.3854. Min Act: -0.0000

Data Index: 794243 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 2.7249. Min Range: -2.7249

Max Act: 2.6241. Min Act: -0.0000

Data Index: 1048124 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 2.7249. Min Range: -2.7249

Max Act: 2.4520. Min Act: -0.0000

Data Index: 736758 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 2.7249. Min Range: -2.7249

Max Act: 2.5326. Min Act: -0.0000

Data Index: 478036 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 2.7249. Min Range: -2.7249

Max Act: 2.3977. Min Act: -0.0000

Data Index: 706443 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 2.7249. Min Range: -2.7249

Max Act: 2.3690. Min Act: -0.0000

Data Index: 827100 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 2.7249. Min Range: -2.7249

Max Act: 2.2466. Min Act: -0.0000

Data Index: 112141 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 2.7249. Min Range: -2.7249

Max Act: 2.2147. Min Act: -0.0000

Data Index: 1300337 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 2.7249. Min Range: -2.7249

Max Act: 2.1353. Min Act: -0.0000

Data Index: 924034 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 2.7249. Min Range: -2.7249

Max Act: 1.9922. Min Act: -0.0000

Data Index: 403367 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 2.7249. Min Range: -2.7249

Max Act: 2.2163. Min Act: -0.0000

Data Index: 777816 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 2.7249. Min Range: -2.7249

Max Act: 2.2071. Min Act: -0.0000

Data Index: 1195138 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 2.7249. Min Range: -2.7249

Max Act: 2.2036. Min Act: -0.0000

Data Index: 1043986 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 2.7249. Min Range: -2.7249

Max Act: 2.3253. Min Act: -0.0000

Data Index: 1323460 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 2.7249. Min Range: -2.7249

Max Act: 2.1859. Min Act: -0.0000

Data Index: 314947 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 2.7249. Min Range: -2.7249

Max Act: 2.1583. Min Act: -0.0000

Data Index: 1305376 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 2.7249. Min Range: -2.7249

Max Act: 2.1460. Min Act: -0.0000

Data Index: 1092128 (C4 (Web Text))

Max Activating Token Index: 632