Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4145 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0787. Min Range: -1.0787

Max Act: 1.0787. Min Act: -0.0001

Data Index: 1263928 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 1.0787. Min Range: -1.0787

Max Act: 1.0563. Min Act: -0.0001

Data Index: 262821 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.9131. Min Act: -0.0001

Data Index: 291361 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.9812. Min Act: -0.0001

Data Index: 358221 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 1.0787. Min Range: -1.0787

Max Act: 1.0369. Min Act: -0.0001

Data Index: 1094588 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.9013. Min Act: -0.0001

Data Index: 616629 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.9673. Min Act: -0.0001

Data Index: 90708 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.9297. Min Act: -0.0001

Data Index: 892218 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.8275. Min Act: -0.0001

Data Index: 1250483 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.8906. Min Act: -0.0001

Data Index: 1008051 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.9521. Min Act: -0.0001

Data Index: 298150 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.9204. Min Act: -0.0001

Data Index: 484667 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.9273. Min Act: -0.0001

Data Index: 839534 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.9457. Min Act: -0.0001

Data Index: 1157337 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.9472. Min Act: -0.0001

Data Index: 381296 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.9359. Min Act: -0.0001

Data Index: 373222 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.9463. Min Act: -0.0001

Data Index: 802754 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.9095. Min Act: -0.0001

Data Index: 1120189 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.8919. Min Act: -0.0001

Data Index: 963282 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.7796. Min Act: -0.0001

Data Index: 389194 (C4 (Web Text))

Max Activating Token Index: 669