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

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

Neuron 1284 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.3271. Min Act: -0.0001

Data Index: 29441 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.3105. Min Act: -0.0001

Data Index: 604165 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2948. Min Act: -0.0000

Data Index: 685093 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2742. Min Act: -0.0000

Data Index: 925 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2750. Min Act: -0.0001

Data Index: 1264160 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2674. Min Act: -0.0001

Data Index: 455111 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2844. Min Act: -0.0001

Data Index: 327264 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2636. Min Act: -0.0001

Data Index: 711991 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2542. Min Act: -0.0001

Data Index: 264637 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2465. Min Act: -0.0000

Data Index: 608670 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2414. Min Act: -0.0001

Data Index: 61070 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2581. Min Act: -0.0001

Data Index: 1252075 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2510. Min Act: -0.0001

Data Index: 1312884 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2323. Min Act: -0.0000

Data Index: 996155 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2544. Min Act: -0.0001

Data Index: 192217 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2252. Min Act: -0.0001

Data Index: 1109389 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2228. Min Act: -0.0000

Data Index: 638355 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2146. Min Act: -0.0000

Data Index: 721214 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2405. Min Act: -0.0001

Data Index: 1309672 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2232. Min Act: -0.0001

Data Index: 49997 (C4 (Web Text))

Max Activating Token Index: 745