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

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

Neuron 5657 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2956. Min Range: -2.2956

Max Act: 2.2956. Min Act: -0.0000

Data Index: 1004496 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.8568. Min Act: -0.0000

Data Index: 1181447 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.8853. Min Act: -0.0000

Data Index: 112147 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.9636. Min Act: -0.0000

Data Index: 266783 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.9138. Min Act: -0.0000

Data Index: 1310083 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 2.2956. Min Range: -2.2956

Max Act: 2.0329. Min Act: -0.0000

Data Index: 356696 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.9215. Min Act: -0.0000

Data Index: 653907 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.9821. Min Act: -0.0000

Data Index: 134374 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.8034. Min Act: -0.0000

Data Index: 1286219 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.7858. Min Act: -0.0000

Data Index: 441758 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.6898. Min Act: -0.0000

Data Index: 838249 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.7178. Min Act: -0.0000

Data Index: 1003500 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.6363. Min Act: -0.0000

Data Index: 489126 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.7772. Min Act: -0.0000

Data Index: 417082 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.6713. Min Act: -0.0000

Data Index: 832733 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.4497. Min Act: -0.0000

Data Index: 344557 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.4309. Min Act: -0.0000

Data Index: 1019418 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.5225. Min Act: -0.0000

Data Index: 105312 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.5017. Min Act: -0.0000

Data Index: 147906 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 2.2956. Min Range: -2.2956

Max Act: 1.3309. Min Act: -0.0000

Data Index: 1318403 (C4 (Web Text))

Max Activating Token Index: 224