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

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

Neuron 833 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.5173. Min Act: -0.0001

Data Index: 23409 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.4838. Min Act: -0.0001

Data Index: 1112965 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.4716. Min Act: -0.0001

Data Index: 488418 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.4716. Min Act: -0.0001

Data Index: 1001600 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.4239. Min Act: -0.0001

Data Index: 964638 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.4449. Min Act: -0.0001

Data Index: 1168406 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.4582. Min Act: -0.0001

Data Index: 316068 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.4276. Min Act: -0.0001

Data Index: 940084 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.4212. Min Act: -0.0001

Data Index: 155224 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.4334. Min Act: -0.0001

Data Index: 31428 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.4090. Min Act: -0.0001

Data Index: 258111 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.4463. Min Act: -0.0001

Data Index: 804803 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.4159. Min Act: -0.0001

Data Index: 534363 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.4545. Min Act: -0.0001

Data Index: 173125 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.4246. Min Act: -0.0001

Data Index: 1279943 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.3943. Min Act: -0.0001

Data Index: 10454 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.4408. Min Act: -0.0001

Data Index: 1063520 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.4179. Min Act: -0.0001

Data Index: 251187 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.4179. Min Act: -0.0001

Data Index: 154372 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.4160. Min Act: -0.0001

Data Index: 1090592 (C4 (Web Text))

Max Activating Token Index: 753