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

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

Neuron 4838 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: 4.7475. Min Range: -4.7475

Max Act: 4.7475. Min Act: -0.0000

Data Index: 406305 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 4.7475. Min Range: -4.7475

Max Act: 4.0341. Min Act: -0.0000

Data Index: 482088 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 4.7475. Min Range: -4.7475

Max Act: 4.0383. Min Act: -0.0000

Data Index: 1250458 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 4.7475. Min Range: -4.7475

Max Act: 3.7882. Min Act: -0.0000

Data Index: 1080369 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 4.7475. Min Range: -4.7475

Max Act: 3.8451. Min Act: -0.0000

Data Index: 856952 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 4.7475. Min Range: -4.7475

Max Act: 3.8156. Min Act: -0.0000

Data Index: 565824 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 4.7475. Min Range: -4.7475

Max Act: 3.4252. Min Act: -0.0000

Data Index: 749250 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 4.7475. Min Range: -4.7475

Max Act: 3.3866. Min Act: -0.0000

Data Index: 152851 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 4.7475. Min Range: -4.7475

Max Act: 3.5490. Min Act: -0.0000

Data Index: 681000 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 4.7475. Min Range: -4.7475

Max Act: 3.3926. Min Act: -0.0000

Data Index: 102017 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 4.7475. Min Range: -4.7475

Max Act: 3.5114. Min Act: -0.0000

Data Index: 576515 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 4.7475. Min Range: -4.7475

Max Act: 3.5314. Min Act: -0.0000

Data Index: 1199769 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 4.7475. Min Range: -4.7475

Max Act: 3.2183. Min Act: -0.0000

Data Index: 1160995 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 4.7475. Min Range: -4.7475

Max Act: 3.5002. Min Act: -0.0000

Data Index: 983367 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 4.7475. Min Range: -4.7475

Max Act: 3.5674. Min Act: -0.0000

Data Index: 900639 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 4.7475. Min Range: -4.7475

Max Act: 3.5621. Min Act: -0.0000

Data Index: 1125212 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 4.7475. Min Range: -4.7475

Max Act: 3.2521. Min Act: -0.0000

Data Index: 565364 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 4.7475. Min Range: -4.7475

Max Act: 3.3942. Min Act: -0.0000

Data Index: 201968 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 4.7475. Min Range: -4.7475

Max Act: 3.3649. Min Act: -0.0000

Data Index: 1237275 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 4.7475. Min Range: -4.7475

Max Act: 3.1884. Min Act: -0.0000

Data Index: 836636 (C4 (Web Text))

Max Activating Token Index: 654