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

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

Neuron 2465 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: 3.7103. Min Range: -3.7103

Max Act: 3.7103. Min Act: -0.0001

Data Index: 352091 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 3.7103. Min Range: -3.7103

Max Act: 3.4162. Min Act: -0.0001

Data Index: 257478 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 3.7103. Min Range: -3.7103

Max Act: 3.2486. Min Act: -0.0001

Data Index: 261076 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 3.7103. Min Range: -3.7103

Max Act: 3.3001. Min Act: -0.0001

Data Index: 294882 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 3.7103. Min Range: -3.7103

Max Act: 2.9253. Min Act: -0.0001

Data Index: 1330548 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 3.7103. Min Range: -3.7103

Max Act: 2.9042. Min Act: -0.0001

Data Index: 1359192 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 3.7103. Min Range: -3.7103

Max Act: 2.7405. Min Act: -0.0001

Data Index: 682711 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 3.7103. Min Range: -3.7103

Max Act: 2.7413. Min Act: -0.0001

Data Index: 1194406 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 3.7103. Min Range: -3.7103

Max Act: 2.7330. Min Act: -0.0001

Data Index: 843071 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 3.7103. Min Range: -3.7103

Max Act: 2.6787. Min Act: -0.0001

Data Index: 435322 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 3.7103. Min Range: -3.7103

Max Act: 2.5944. Min Act: -0.0001

Data Index: 507360 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 3.7103. Min Range: -3.7103

Max Act: 2.1904. Min Act: -0.0001

Data Index: 352402 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 3.7103. Min Range: -3.7103

Max Act: 2.5362. Min Act: -0.0001

Data Index: 1057361 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 3.7103. Min Range: -3.7103

Max Act: 2.5327. Min Act: -0.0001

Data Index: 774078 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 3.7103. Min Range: -3.7103

Max Act: 2.4008. Min Act: -0.0001

Data Index: 1261315 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 3.7103. Min Range: -3.7103

Max Act: 2.6118. Min Act: -0.0001

Data Index: 443423 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 3.7103. Min Range: -3.7103

Max Act: 2.3709. Min Act: -0.0001

Data Index: 1259287 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 3.7103. Min Range: -3.7103

Max Act: 2.3744. Min Act: -0.0001

Data Index: 291607 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 3.7103. Min Range: -3.7103

Max Act: 2.3679. Min Act: -0.0001

Data Index: 68410 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 3.7103. Min Range: -3.7103

Max Act: 2.3695. Min Act: -0.0001

Data Index: 701104 (C4 (Web Text))

Max Activating Token Index: 435