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

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

Neuron 1287 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6079. Min Range: -4.6079

Max Act: 4.6079. Min Act: -0.0001

Data Index: 326221 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 4.6079. Min Range: -4.6079

Max Act: 3.9945. Min Act: -0.0000

Data Index: 900125 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 4.6079. Min Range: -4.6079

Max Act: 3.5874. Min Act: -0.0001

Data Index: 1210225 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 4.6079. Min Range: -4.6079

Max Act: 2.6136. Min Act: -0.0000

Data Index: 1082183 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 4.6079. Min Range: -4.6079

Max Act: 2.6448. Min Act: -0.0000

Data Index: 749360 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 4.6079. Min Range: -4.6079

Max Act: 2.5050. Min Act: -0.0001

Data Index: 559173 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 4.6079. Min Range: -4.6079

Max Act: 2.6121. Min Act: -0.0000

Data Index: 779316 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 4.6079. Min Range: -4.6079

Max Act: 2.5394. Min Act: -0.0000

Data Index: 1126056 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 4.6079. Min Range: -4.6079

Max Act: 2.4147. Min Act: -0.0001

Data Index: 1326322 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 4.6079. Min Range: -4.6079

Max Act: 2.5321. Min Act: -0.0000

Data Index: 524503 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 4.6079. Min Range: -4.6079

Max Act: 2.5532. Min Act: -0.0001

Data Index: 949170 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 4.6079. Min Range: -4.6079

Max Act: 2.5316. Min Act: -0.0000

Data Index: 335954 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 4.6079. Min Range: -4.6079

Max Act: 2.2927. Min Act: -0.0001

Data Index: 1245446 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 4.6079. Min Range: -4.6079

Max Act: 2.2931. Min Act: -0.0000

Data Index: 456339 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 4.6079. Min Range: -4.6079

Max Act: 2.2574. Min Act: -0.0000

Data Index: 1316883 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 4.6079. Min Range: -4.6079

Max Act: 2.4014. Min Act: -0.0000

Data Index: 292575 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 4.6079. Min Range: -4.6079

Max Act: 2.2726. Min Act: -0.0000

Data Index: 319111 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 4.6079. Min Range: -4.6079

Max Act: 2.2587. Min Act: -0.0000

Data Index: 792951 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 4.6079. Min Range: -4.6079

Max Act: 2.3311. Min Act: -0.0000

Data Index: 588089 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 4.6079. Min Range: -4.6079

Max Act: 2.0722. Min Act: -0.0000

Data Index: 1124983 (C4 (Web Text))

Max Activating Token Index: 194