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

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

Neuron 3684 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.5427. Min Act: -0.0001

Data Index: 1102648 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.5300. Min Act: -0.0000

Data Index: 121282 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.5344. Min Act: -0.0001

Data Index: 513037 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.5488. Min Act: -0.0001

Data Index: 1302881 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.5263. Min Act: -0.0001

Data Index: 413761 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.5208. Min Act: -0.0001

Data Index: 958435 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.5181. Min Act: -0.0001

Data Index: 1304965 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4957. Min Act: -0.0001

Data Index: 915716 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.5053. Min Act: -0.0001

Data Index: 783931 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4798. Min Act: -0.0001

Data Index: 841370 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4938. Min Act: -0.0001

Data Index: 1368474 (Python Code)

Max Activating Token Index: 968

Text #11

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1980 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4757. Min Act: -0.0001

Data Index: 590880 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4774. Min Act: -0.0001

Data Index: 284922 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4599. Min Act: -0.0001

Data Index: 95466 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4479. Min Act: -0.0001

Data Index: 916215 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4387. Min Act: -0.0001

Data Index: 522924 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4719. Min Act: -0.0001

Data Index: 1151227 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4491. Min Act: -0.0001

Data Index: 757855 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.5488. Min Range: -0.5488

Max Act: 0.4863. Min Act: -0.0001

Data Index: 92517 (C4 (Web Text))

Max Activating Token Index: 897