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

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

Neuron 4941 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.8112. Min Act: -0.0000

Data Index: 373434 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.4518. Min Act: -0.0000

Data Index: 211966 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.3405. Min Act: -0.0000

Data Index: 1172846 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.3276. Min Act: -0.0000

Data Index: 910004 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.2867. Min Act: -0.0000

Data Index: 837615 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.3666. Min Act: -0.0000

Data Index: 899655 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.2776. Min Act: -0.0000

Data Index: 242377 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.2043. Min Act: -0.0000

Data Index: 511052 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.2702. Min Act: -0.0000

Data Index: 1128878 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.2569. Min Act: -0.0000

Data Index: 398403 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.2316. Min Act: -0.0000

Data Index: 1206396 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.2239. Min Act: -0.0000

Data Index: 207747 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.2084. Min Act: -0.0000

Data Index: 886862 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.2081. Min Act: -0.0000

Data Index: 301716 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.1227. Min Act: -0.0000

Data Index: 748217 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.1152. Min Act: -0.0000

Data Index: 1301429 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.1740. Min Act: -0.0000

Data Index: 721988 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.1658. Min Act: -0.0000

Data Index: 878325 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.1335. Min Act: -0.0000

Data Index: 880897 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 1.8112. Min Range: -1.8112

Max Act: 1.0663. Min Act: -0.0000

Data Index: 1200000 (C4 (Web Text))

Max Activating Token Index: 568