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

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

Neuron 1498 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8991. Min Act: -0.0000

Data Index: 245901 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6937. Min Act: -0.0001

Data Index: 230433 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1108262 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.4731. Min Act: -0.0000

Data Index: 1335780 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.5005. Min Act: -0.0000

Data Index: 1181464 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.4855. Min Act: -0.0001

Data Index: 491445 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.4825. Min Act: -0.0000

Data Index: 70392 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.4986. Min Act: -0.0000

Data Index: 850062 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.4640. Min Act: -0.0000

Data Index: 16002 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.4723. Min Act: -0.0001

Data Index: 710403 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.4535. Min Act: -0.0001

Data Index: 354663 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.4459. Min Act: -0.0001

Data Index: 1201876 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.4375. Min Act: -0.0001

Data Index: 631944 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.4112. Min Act: -0.0001

Data Index: 913936 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.4226. Min Act: -0.0001

Data Index: 761668 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.4182. Min Act: -0.0000

Data Index: 929460 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.3942. Min Act: -0.0001

Data Index: 392724 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.4030. Min Act: -0.0001

Data Index: 503494 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1202992 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.4027. Min Act: -0.0000

Data Index: 299450 (C4 (Web Text))

Max Activating Token Index: 145