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

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

Neuron 2622 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.3455. Min Act: -0.0001

Data Index: 503004 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2987. Min Act: -0.0000

Data Index: 578426 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.3206. Min Act: -0.0001

Data Index: 1163825 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2800. Min Act: -0.0001

Data Index: 1140923 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2814. Min Act: -0.0001

Data Index: 1205166 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2638. Min Act: -0.0000

Data Index: 821890 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2566. Min Act: -0.0001

Data Index: 47468 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2439. Min Act: -0.0000

Data Index: 36150 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2380. Min Act: -0.0000

Data Index: 1271109 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2477. Min Act: -0.0001

Data Index: 150747 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1216339 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2145. Min Act: -0.0001

Data Index: 273010 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2215. Min Act: -0.0000

Data Index: 571319 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2191. Min Act: -0.0000

Data Index: 1161990 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2088. Min Act: -0.0000

Data Index: 1196288 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2301. Min Act: -0.0000

Data Index: 481400 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2182. Min Act: -0.0000

Data Index: 1202725 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.1958. Min Act: -0.0001

Data Index: 928383 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2090. Min Act: -0.0000

Data Index: 398795 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2208. Min Act: -0.0001

Data Index: 525387 (C4 (Web Text))

Max Activating Token Index: 259