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

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

Neuron 2120 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: 2.8518. Min Range: -2.8518

Max Act: 2.7474. Min Act: -0.0000

Data Index: 318864 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 2.8518. Min Range: -2.8518

Max Act: 2.8518. Min Act: -0.0000

Data Index: 949092 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 2.8518. Min Range: -2.8518

Max Act: 2.7394. Min Act: -0.0000

Data Index: 594955 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 2.8518. Min Range: -2.8518

Max Act: 2.3943. Min Act: -0.0000

Data Index: 32262 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 2.8518. Min Range: -2.8518

Max Act: 2.6434. Min Act: -0.0000

Data Index: 658269 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 2.8518. Min Range: -2.8518

Max Act: 2.5881. Min Act: -0.0000

Data Index: 624560 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 2.8518. Min Range: -2.8518

Max Act: 2.4277. Min Act: -0.0000

Data Index: 633515 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 2.8518. Min Range: -2.8518

Max Act: 2.4540. Min Act: -0.0000

Data Index: 731392 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 2.8518. Min Range: -2.8518

Max Act: 2.5102. Min Act: -0.0000

Data Index: 1139013 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 2.8518. Min Range: -2.8518

Max Act: 2.5713. Min Act: -0.0000

Data Index: 1243323 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 2.8518. Min Range: -2.8518

Max Act: 2.4214. Min Act: -0.0000

Data Index: 98358 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 2.8518. Min Range: -2.8518

Max Act: 2.4067. Min Act: -0.0000

Data Index: 767137 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 2.8518. Min Range: -2.8518

Max Act: 2.2454. Min Act: -0.0000

Data Index: 712363 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 2.8518. Min Range: -2.8518

Max Act: 2.3686. Min Act: -0.0000

Data Index: 1014479 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 2.8518. Min Range: -2.8518

Max Act: 2.3695. Min Act: -0.0000

Data Index: 1238527 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 2.8518. Min Range: -2.8518

Max Act: 2.3524. Min Act: -0.0000

Data Index: 482109 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 2.8518. Min Range: -2.8518

Max Act: 2.4714. Min Act: -0.0000

Data Index: 424253 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 2.8518. Min Range: -2.8518

Max Act: 2.1993. Min Act: -0.0000

Data Index: 823028 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 2.8518. Min Range: -2.8518

Max Act: 2.3476. Min Act: -0.0000

Data Index: 1296220 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 2.8518. Min Range: -2.8518

Max Act: 2.3192. Min Act: -0.0000

Data Index: 1304588 (C4 (Web Text))

Max Activating Token Index: 661