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

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

Neuron 3686 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: 0.5630. Min Range: -0.5630

Max Act: 0.5206. Min Act: -0.0001

Data Index: 1144534 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.5630. Min Act: -0.0001

Data Index: 833767 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.5566. Min Act: -0.0000

Data Index: 150524 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4700. Min Act: -0.0001

Data Index: 979023 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4331. Min Act: -0.0001

Data Index: 423314 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4603. Min Act: -0.0001

Data Index: 216677 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4262. Min Act: -0.0000

Data Index: 429129 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4407. Min Act: -0.0001

Data Index: 656392 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4565. Min Act: -0.0001

Data Index: 287832 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4444. Min Act: -0.0000

Data Index: 127264 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.3513. Min Act: -0.0001

Data Index: 124490 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4442. Min Act: -0.0001

Data Index: 237557 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.3976. Min Act: -0.0001

Data Index: 1177355 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4091. Min Act: -0.0000

Data Index: 615168 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.3946. Min Act: -0.0001

Data Index: 451887 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.3890. Min Act: -0.0001

Data Index: 131139 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4306. Min Act: -0.0001

Data Index: 121113 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4294. Min Act: -0.0001

Data Index: 1293373 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.4300. Min Act: -0.0001

Data Index: 276381 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.5630. Min Range: -0.5630

Max Act: 0.3970. Min Act: -0.0001

Data Index: 1189892 (C4 (Web Text))

Max Activating Token Index: 147