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

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

Neuron 1617 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.3069. Min Act: -0.0001

Data Index: 1267453 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2644. Min Act: -0.0001

Data Index: 895153 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2583. Min Act: -0.0001

Data Index: 4325 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2540. Min Act: -0.0001

Data Index: 866474 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2599. Min Act: -0.0001

Data Index: 591933 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2480. Min Act: -0.0001

Data Index: 1248317 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2412. Min Act: -0.0001

Data Index: 748165 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2271. Min Act: -0.0001

Data Index: 135793 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2433. Min Act: -0.0001

Data Index: 107881 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2411. Min Act: -0.0001

Data Index: 753227 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2319. Min Act: -0.0001

Data Index: 285676 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2338. Min Act: -0.0001

Data Index: 983657 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2098. Min Act: -0.0001

Data Index: 561284 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2423. Min Act: -0.0001

Data Index: 1137365 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2324. Min Act: -0.0001

Data Index: 960755 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2069. Min Act: -0.0001

Data Index: 731683 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2160. Min Act: -0.0001

Data Index: 456245 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2214. Min Act: -0.0001

Data Index: 214825 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2191. Min Act: -0.0001

Data Index: 880978 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2272. Min Act: -0.0001

Data Index: 469220 (C4 (Web Text))

Max Activating Token Index: 605